© 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. 32-TRANSCODER-HP
    7. 43186
    Prev
    Next
    INDEX
    Explanations

    hold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     YYS
    -0.28
    å¾Ĺ罪
    -0.25
    olation
    -0.25
    éĻ¢éķ¿
    -0.25
    _DECLS
    -0.24
     Ost
    -0.24
    faction
    -0.24
    麸
    -0.24
    ä¹ŁæĹłæ³ķ
    -0.24
    èĢħçļĦ
    -0.23
    POSITIVE LOGITS
    overs
    0.32
     over
    0.30
    onto
    0.30
    raise
    0.30
    over
    0.29
     onto
    0.29
    ornado
    0.28
    ä¸Ģä¼ļ
    0.28
     open
    0.28
    raised
    0.27
    Activations Density 0.010%

    No Known Activations