© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108604
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    South
    -0.27
    ãģªãģĭãģªãģĭ
    -0.26
    Custom
    -0.25
    phy
    -0.25
     ----------------------------------------------------------------------------
    -0.25
    TC
    -0.25
    dos
    -0.25
    U
    -0.25
    share
    -0.24
    G
    -0.24
    POSITIVE LOGITS
    -bel
    0.28
    createClass
    0.27
    å¹ħ
    0.26
     Charges
    0.26
    |int
    0.25
    sonian
    0.25
    mó
    0.25
    esting
    0.24
    -important
    0.24
    /embed
    0.24
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.