© 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. 30-TRANSCODER-HP
    7. 96378
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nock
    -0.27
    idl
    -0.26
    pite
    -0.25
     Freund
    -0.24
    oller
    -0.24
     деле
    -0.24
     phosph
    -0.24
    á»ĵi
    -0.24
    ornment
    -0.24
    icolor
    -0.23
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    0.32
    eted
    0.30
     QQ
    0.28
    edly
    0.27
    compet
    0.25
    çĦĬ
    0.25
    essa
    0.24
    åĩºåıij
    0.24
    ately
    0.24
    otted
    0.24
    Activations Density 0.890%

    No Known Activations

    This feature has no known activations.