© 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. 33-TRANSCODER-HP
    7. 54140
    Prev
    Next
    INDEX
    Explanations

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypad
    -0.29
    iard
    -0.28
    isz
    -0.28
    èĢ¦
    -0.27
    èŁĴ
    -0.26
    æ²Ļ
    -0.26
    çIJĨæĢ§
    -0.25
    LOCKS
    -0.25
    pton
    -0.24
    롱
    -0.23
    POSITIVE LOGITS
    è¿ĩ
    0.41
     sense
    0.32
     increasing
    0.31
     growing
    0.31
     ex
    0.31
     over
    0.30
    éģİ
    0.29
     st
    0.28
    éĺµ
    0.26
    ause
    0.26
    Activations Density 0.032%

    No Known Activations