© 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. 107480
    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
     Outlet
    -0.27
     themselves
    -0.27
    finder
    -0.27
     yourselves
    -0.27
    æĢİä¹Ī说
    -0.25
    ittance
    -0.25
    Spacer
    -0.24
    erset
    -0.24
    alyzer
    -0.24
    endcode
    -0.23
    POSITIVE LOGITS
    ãģķãĤī
    0.29
    ousse
    0.27
     acquaintance
    0.26
    wój
    0.25
    ilians
    0.25
     Clair
    0.25
    ÑĩÑĥв
    0.25
    eva
    0.24
     acquaint
    0.24
    oS
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.