© 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. 97750
    Prev
    Next
    INDEX
    Explanations

    Code and copyright notices

    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
    rete
    -0.34
     ëıĻìĭľ
    -0.31
    itulo
    -0.30
    æĦıåij³
    -0.28
    á»ıi
    -0.25
    è¯ģæį®
    -0.24
    @Module
    -0.23
    rei
    -0.23
    pai
    -0.23
    å¾®åŀĭ
    -0.23
    POSITIVE LOGITS
     ends
    0.29
     ended
    0.28
    ends
    0.28
     spat
    0.26
    en
    0.24
    EN
    0.24
    å£ķ
    0.24
    venue
    0.24
    ç»ĵå±Ģ
    0.24
    ç»ĵæĿŁäºĨ
    0.23
    Activations Density 0.006%

    No Known Activations