© 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. 32-TRANSCODER-HP
    7. 42654
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     th
    -1.25
    	th
    -0.87
    -th
    -0.85
     ther
    -0.79
    th
    -0.78
    .th
    -0.77
    (th
    -0.77
    _th
    -0.75
     thi
    -0.73
    <th
    -0.71
    POSITIVE LOGITS
    端æŃ£
    0.27
    éļ¼
    0.26
    æİ¥è¿ij
    0.25
    çĶļèĩ³
    0.25
    ắc
    0.25
    ä½Ĩæĺ¯
    0.24
    åıĪ被
    0.23
    éĥ¨ä¸»ä»»
    0.23
    isk
    0.23
    åı£å¤´
    0.23
    Activations Density 0.000%

    No Known Activations