© 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. 23414
    Prev
    Next
    INDEX
    Explanations

    Programming code/licenses/warnings

    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
     Farmer
    -0.26
     `_
    -0.26
    ophile
    -0.26
    зд
    -0.26
     feature
    -0.25
     DP
    -0.25
     close
    -0.25
     Vi
    -0.24
    encion
    -0.24
    --
    -0.23
    POSITIVE LOGITS
    æŁĦ
    0.30
    åı¦ä¸Ģè¾¹
    0.27
     anymore
    0.27
    ç°¿
    0.26
    è¿ĩæĿ¥
    0.25
    åªĴ
    0.25
    incorrect
    0.25
    åıĺäºĨ
    0.25
    averse
    0.24
    éĶĻäºĨ
    0.24
    Activations Density 0.940%

    No Known Activations