© 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. 9-TRANSCODER-HP
    7. 29277
    Prev
    Next
    INDEX
    Explanations

    she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĩªçIJĨ
    -0.28
    olum
    -0.27
     Freed
    -0.27
    åijĬè¯ī她
    -0.25
    åıij声
    -0.25
    rist
    -0.25
    .prepend
    -0.25
    åıijåħī
    -0.24
    è¿Ļæł·
    -0.24
    CDATA
    -0.23
    POSITIVE LOGITS
    tere
    0.28
     tech
    0.27
    è´±
    0.27
    tech
    0.26
    åĩ¡
    0.25
    é¡¿
    0.25
    Ctrls
    0.24
    æ·¡
    0.24
    éĩį
    0.24
    .assignment
    0.24
    Activations Density 11.685%

    No Known Activations