© 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. 38591
    Prev
    Next
    INDEX
    Explanations

    programming/technical text

    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
    æ£ĭ
    -0.26
    æĮ¤
    -0.25
     Lös
    -0.25
    éģŃåĪ°
    -0.24
    æ²ī
    -0.24
    åĨĻçļĦ
    -0.24
    Geometry
    -0.23
    ogl
    -0.23
    ê
    -0.23
    ä¾Ľ
    -0.23
    POSITIVE LOGITS
    gether
    0.37
    ories
    0.33
    aces
    0.31
    antee
    0.30
    ory
    0.30
    ceans
    0.29
    alice
    0.28
    akening
    0.28
    iant
    0.28
    portun
    0.28
    Activations Density 1.308%

    No Known Activations