© 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. 9-TRANSCODER-HP
    7. 29833
    Prev
    Next
    INDEX
    Explanations

    mm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quila
    -0.28
    _INCLUDED
    -0.27
    entina
    -0.27
    rix
    -0.26
    arella
    -0.25
    æ¦Ľ
    -0.25
    ä»ij
    -0.25
    æıIJåıĬ
    -0.25
    lah
    -0.25
     straight
    -0.24
    POSITIVE LOGITS
    åĪ¤
    0.28
    åĮºåĿĹ
    0.27
     ethic
    0.25
    ç§į
    0.25
    íijľ
    0.24
    éĩľ
    0.24
    objectId
    0.24
    æ²ĥå°Ķ
    0.24
     Budget
    0.24
     filib
    0.24
    Activations Density 1.663%

    No Known Activations