© 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. 130178
    Prev
    Next
    INDEX
    Explanations

    Results, outcomes, conclusions

    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
    acci
    -0.28
     Proper
    -0.25
     proper
    -0.25
    ombo
    -0.25
     atrav
    -0.25
    зам
    -0.24
     acompan
    -0.24
     Trophy
    -0.23
    ãģĵãģ¨ãģ§ãģĻ
    -0.23
    زÙĪ
    -0.23
    POSITIVE LOGITS
     resulting
    0.68
    ç»ĵæŀľ
    0.53
     resultant
    0.52
    çļĦç»ĵæŀľ
    0.50
     resulted
    0.49
    æīĢå¾Ĺ
    0.46
    çµIJæŀľ
    0.44
    ç»ĵæŀľæĺ¾ç¤º
    0.44
    .result
    0.39
     ensuing
    0.36
    Activations Density 0.009%

    No Known Activations