© 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. 23-TRANSCODER-HP
    7. 23830
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifax
    -0.26
    åĬłå·¥åİĤ
    -0.26
    /legal
    -0.26
    .getvalue
    -0.26
    _DAYS
    -0.24
    Pinterest
    -0.24
    .overflow
    -0.24
    墦
    -0.24
    转ä¼ļ
    -0.24
    æĢ»éĿ¢ç§¯
    -0.24
    POSITIVE LOGITS
    å£°éŁ³
    0.57
    身影
    0.57
    çļĦå£°éŁ³
    0.50
    çĨŁæĤīçļĦ
    0.47
    èģ²éŁ³
    0.46
     voices
    0.45
    çļĦ身影
    0.45
     voice
    0.41
     sounds
    0.40
     familiar
    0.39
    Activations Density 0.006%

    No Known Activations