© 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. 31-TRANSCODER-HP
    7. 18721
    Prev
    Next
    INDEX
    Explanations

    Institutions, education, people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     packed
    -0.30
    樾
    -0.29
    chin
    -0.29
    æīĵåĮħ
    -0.27
    ;left
    -0.26
    æµĨ
    -0.26
     Education
    -0.25
    eks
    -0.25
     healed
    -0.24
    å¨ij
    -0.24
    POSITIVE LOGITS
    ä¸įå¼Ģ
    0.28
    selectAll
    0.28
     presume
    0.27
    åľĥ
    0.26
    åħĭæĭī
    0.26
    STALL
    0.26
    [method
    0.26
    ewater
    0.25
     associates
    0.25
     PPP
    0.24
    Activations Density 0.048%

    No Known Activations