© 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. 25396
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    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
    è§Ĵ
    -0.27
     angle
    -0.26
    åĽ¢åľĨ
    -0.26
    çļĦç²¾ç¥ŀ
    -0.25
    redi
    -0.25
    ationToken
    -0.25
    Ĩµ
    -0.24
    eken
    -0.24
    -thread
    -0.24
    floor
    -0.24
    POSITIVE LOGITS
     uniquely
    0.32
    SI
    0.28
    nest
    0.28
    æģ¶
    0.27
    个æĢ§
    0.26
     dedicated
    0.25
    CBS
    0.24
    ä¸Ńæĸ¹
    0.24
    |unique
    0.24
    qual
    0.24
    Activations Density 0.003%

    No Known Activations