© 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. 95776
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    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
    åľ¨éĤ£éĩĮ
    -0.38
    åľ¨è¿ĻéĩĮ
    -0.36
     here
    -0.33
    åľ¨åĵªéĩĮ
    -0.30
    åľ¨åĮĹ京
    -0.30
    è¿ĻéĩĮæľī
    -0.29
    éĤ£éĩĮ
    -0.29
     duel
    -0.28
    @g
    -0.27
    è¿ĻéĩĮ
    -0.26
    POSITIVE LOGITS
     Esc
    0.30
    umbles
    0.30
     the
    0.28
    iek
    0.28
    åºŁ
    0.28
     Turn
    0.27
    Turn
    0.27
     Mess
    0.27
    +'.
    0.26
     La
    0.26
    Activations Density 0.912%

    No Known Activations