© 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. 23-TRANSCODER-HP
    7. 23499
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĩĿèģļåĬĽ
    -0.31
    å¼¹
    -0.30
    åºķå±Ĥ
    -0.28
    æĮ¨
    -0.25
    recht
    -0.25
    æµıè§ĪåĻ¨
    -0.25
    èĢIJå¿ĥ
    -0.25
    åIJĪè§Ħ
    -0.24
    å¹³åĩ¡
    -0.24
    å¼ŁåħĦ
    -0.24
    POSITIVE LOGITS
     feather
    0.28
    æ±°
    0.25
    aras
    0.25
     miscellaneous
    0.25
     projected
    0.24
     pet
    0.24
     ÑĦак
    0.24
    aking
    0.23
     ¶
    0.23
     osc
    0.23
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.