© 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. 112099
    Prev
    Next
    INDEX
    Explanations

    Online discussions with a problem

    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
    åIJĮæł·
    -0.27
    @endsection
    -0.26
    溶
    -0.25
    cg
    -0.25
    åı¦ä¸Ģè¾¹
    -0.23
    isors
    -0.23
    æĪIJ交
    -0.23
    óng
    -0.23
    oth
    -0.23
    ä½ıéĻ¢
    -0.23
    POSITIVE LOGITS
    ä¸įçĪ±
    0.35
     dislike
    0.32
    ä¸įåĸľæ¬¢
    0.32
     kil
    0.29
    ä¸įæĦ¿
    0.29
    ä¸į认è¯Ĩ
    0.29
     refusal
    0.28
    ä¸įæĦ¿æĦı
    0.27
     mistr
    0.26
     disliked
    0.26
    Activations Density 0.004%

    No Known Activations