© 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. 12-TRANSCODER-HP
    7. 22368
    Prev
    Next
    INDEX
    Explanations

    forum/conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fragment
    -0.27
    GI
    -0.26
    hi
    -0.26
     Reverse
    -0.26
     Hi
    -0.26
     reverse
    -0.25
    sil
    -0.25
    äºĮç»´çłģ
    -0.24
     terminator
    -0.24
    翦
    -0.24
    POSITIVE LOGITS
    åݻ年åIJĮæľŁ
    0.28
    åı¦ä¸Ģ个
    0.27
    å½¢
    0.27
    NASDAQ
    0.26
    agens
    0.25
    åݻ年
    0.25
    æįī
    0.25
    åįĬå¹´
    0.24
    éĻ·
    0.24
    ä¸ĥæľĪ
    0.24
    Activations Density 0.002%

    No Known Activations