© 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. 23648
    Prev
    Next
    INDEX
    Explanations

    about

    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
     hå
    -0.29
     refuse
    -0.28
     realize
    -0.26
    ино
    -0.25
    lem
    -0.25
    лÑĮн
    -0.25
    éŀį
    -0.25
    æĦıä¹īä¸ĬçļĦ
    -0.25
     Junction
    -0.25
    formatter
    -0.24
    POSITIVE LOGITS
     giving
    0.35
    FSIZE
    0.31
     repeat
    0.30
     hitting
    0.28
    ÑĢаг
    0.28
     avoiding
    0.27
     exposing
    0.27
     defeating
    0.27
     harming
    0.26
     vulnerability
    0.26
    Activations Density 0.007%

    No Known Activations