© 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. 108554
    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
    nable
    -0.28
    éĵº
    -0.26
     '::
    -0.25
     grievances
    -0.25
    omatic
    -0.24
     untreated
    -0.24
    éļĻ
    -0.24
    -padding
    -0.24
    mé
    -0.24
    onChange
    -0.23
    POSITIVE LOGITS
    SW
    0.28
    lite
    0.27
    DDL
    0.27
     SW
    0.27
     Swan
    0.27
     Desmond
    0.27
     especial
    0.27
     special
    0.26
     deserted
    0.26
    oba
    0.26
    Activations Density 2.856%

    No Known Activations

    This feature has no known activations.