© 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. 31-TRANSCODER-HP
    7. 19450
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢæŃ¥
    -0.36
     in
    -0.28
    -Time
    -0.28
    åľ¨
    -0.26
    /time
    -0.25
    -time
    -0.25
    ä¸įè¿ľ
    -0.25
    InThe
    -0.25
    æŀ¯
    -0.25
     –
    -0.24
    POSITIVE LOGITS
     the
    0.44
     their
    0.43
     any
    0.40
     its
    0.39
     those
    0.39
     whatever
    0.39
     ensuring
    0.38
     this
    0.38
     maintaining
    0.38
     realizing
    0.37
    Activations Density 8.499%

    No Known Activations