© 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. 22-TRANSCODER-HP
    7. 130238
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.28
    榻
    -0.27
    åİ¿å§Ķ书记
    -0.26
     wore
    -0.25
    agal
    -0.24
     arose
    -0.24
    èµ°å¾Ĺ
    -0.24
    èµ°åĩºæĿ¥
    -0.24
    称åij¼
    -0.23
    out
    -0.23
    POSITIVE LOGITS
    è¿ģ
    0.31
    åħ¥åѦ
    0.27
    ,ev
    0.26
    '||
    0.26
     evacuated
    0.26
    èĴ¸åıij
    0.25
    _ev
    0.25
    åĨħéĥ¨
    0.24
     insensitive
    0.24
    :event
    0.24
    Activations Density 0.013%

    No Known Activations