© 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. 30-TRANSCODER-HP
    7. 96098
    Prev
    Next
    INDEX
    Explanations

    quant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Relax
    -0.27
    ä»ĸèĩªå·±
    -0.26
    翼
    -0.25
    æ¼ĶåĮĸ
    -0.25
    åijĬè¯īä»ĸ
    -0.24
    åĸĻ
    -0.24
    æİĸ
    -0.24
    çļĦçľ¼åħī
    -0.23
    voices
    -0.23
    注éĶĢ
    -0.23
    POSITIVE LOGITS
     quant
    1.07
    quant
    0.88
    Quant
    0.83
     Quant
    0.81
     percent
    0.77
    .quant
    0.77
    _quant
    0.75
    éĩıåĮĸ
    0.69
    percent
    0.69
    .percent
    0.67
    Activations Density 0.952%

    No Known Activations