© 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. 106927
    Prev
    Next
    INDEX
    Explanations

    Geh

    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
    çĽ¸äº²
    -0.25
    (sec
    -0.25
    æµģæ°´
    -0.24
    FontAwesomeIcon
    -0.24
    rap
    -0.23
    ثار
    -0.23
    æ·³
    -0.23
    over
    -0.23
    æŃ»èĢħ
    -0.23
     over
    -0.23
    POSITIVE LOGITS
    社ä¼ļ稳å®ļ
    0.29
    èĤ¤èī²
    0.26
    ethyst
    0.26
    éĤĪ
    0.26
    isu
    0.25
    utow
    0.24
    è´§æºIJ
    0.24
     xor
    0.24
    èĦ¸
    0.24
     пед
    0.23
    Activations Density 0.155%

    No Known Activations