© 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. 95713
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ëĶĶ
    -0.27
     indefinite
    -0.25
    ramento
    -0.25
    aeda
    -0.25
    anza
    -0.25
    å·ŀ
    -0.25
    éĥ¨ä»½
    -0.24
    è§ĦèĮĥ
    -0.24
    åģľå·¥
    -0.24
    little
    -0.23
    POSITIVE LOGITS
    oji
    0.26
    俸
    0.26
    .beta
    0.25
    haust
    0.25
     isl
    0.24
    _Group
    0.24
    ients
    0.23
    (resource
    0.23
    ALSE
    0.23
    æ±ģ
    0.23
    Activations Density 0.950%

    No Known Activations