© 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. 38583
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Arc
    -0.25
     ACM
    -0.25
    (op
    -0.25
     u
    -0.24
    ANNER
    -0.24
    Uvs
    -0.24
     ILogger
    -0.24
     IPS
    -0.24
     aged
    -0.24
     uz
    -0.24
    POSITIVE LOGITS
    åĪ©
    0.35
    å¿ĺ
    0.32
    åħĭ
    0.31
    æķ¢
    0.31
    满
    0.31
    顾
    0.30
    åģľ
    0.30
    ä½Ĩ
    0.30
    åIJ«
    0.29
    çķĻ
    0.29
    Activations Density 61.943%

    No Known Activations