© 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. 38536
    Prev
    Next
    INDEX
    Explanations

    ocean

    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
    Negative Logits
     the
    -0.28
     S
    -0.26
    QRSTUVWXYZ
    -0.25
     RESULTS
    -0.24
     Operations
    -0.24
     Sp
    -0.24
    社交åªĴä½ĵ
    -0.24
    æł·åŃIJ
    -0.24
    èĴĭ
    -0.24
     Sugar
    -0.24
    POSITIVE LOGITS
    -current
    0.43
    -mile
    0.36
    -floor
    0.35
    -average
    0.35
    -strip
    0.35
    -chair
    0.35
    -base
    0.35
    um
    0.35
    -f
    0.34
    -major
    0.34
    Activations Density 1.046%

    No Known Activations