© 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. 109201
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    æİı
    -0.29
    第ä¸Ģ家
    -0.28
    æį
    -0.27
    ellular
    -0.26
    rons
    -0.26
    æ°Ķè´¨
    -0.26
     Fist
    -0.26
    |;↵
    -0.26
    èĢģå©Ĩ
    -0.26
    crets
    -0.25
    POSITIVE LOGITS
    -na
    0.30
     vac
    0.28
     CN
    0.26
     pseud
    0.25
     Terminator
    0.25
    -fin
    0.24
     continuum
    0.24
    平衡
    0.24
     UA
    0.24
    mach
    0.24
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.