© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40459
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æį¢äºĨ
    -0.27
    å§Ķç»Ħç»ĩ
    -0.26
    éĽĨè£ħ
    -0.26
    mö
    -0.25
    uctor
    -0.25
    -tested
    -0.25
    úb
    -0.24
    å¼¼
    -0.24
    uida
    -0.24
    ETO
    -0.24
    POSITIVE LOGITS
     Rock
    0.30
    t
    0.29
     T
    0.28
     Imperial
    0.28
     Sky
    0.27
     sky
    0.27
     un
    0.27
     medieval
    0.27
     central
    0.27
    ian
    0.26
    Activations Density 46.508%

    No Known Activations