© 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. 25-TRANSCODER-HP
    7. 109495
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oola
    -0.30
     PUB
    -0.25
    uples
    -0.25
    imony
    -0.24
    embre
    -0.24
     dam
    -0.24
    åŁŁåIJį
    -0.24
     pub
    -0.23
    quoise
    -0.23
    ä¸ĥæĺŁ
    -0.23
    POSITIVE LOGITS
    interpreted
    0.27
    æķ´çIJĨ
    0.26
     remotely
    0.26
     Discuss
    0.26
    ported
    0.25
     Anal
    0.25
    å¥Ĺè£ħ
    0.24
    pers
    0.24
    å¤ĸ壳
    0.23
    è¹Ĭ
    0.23
    Activations Density 0.914%

    No Known Activations