© 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. 109417
    Prev
    Next
    INDEX
    Explanations

    Ham

    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
    åħ¼
    -0.26
    åĮ¡
    -0.26
    abela
    -0.25
    éĺĶ
    -0.25
    kel
    -0.25
    ÑĤа
    -0.25
     insider
    -0.24
     vice
    -0.24
    RESS
    -0.24
     tá»ĩ
    -0.24
    POSITIVE LOGITS
    AZ
    0.24
     coll
    0.24
    cedures
    0.23
    kits
    0.23
    scheme
    0.23
    è®´
    0.23
    她说
    0.23
     cafes
    0.23
    éĴķ
    0.23
    æ°¨éħ¸
    0.22
    Activations Density 0.120%

    No Known Activations