© 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. 29117
    Prev
    Next
    INDEX
    Explanations

    position

    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
    AIL
    -0.26
    reeze
    -0.26
    ziel
    -0.24
    太大
    -0.24
    ACHI
    -0.24
    éĦ¢
    -0.23
     dominant
    -0.23
    ![
    -0.23
     Derrick
    -0.23
     Ritch
    -0.23
    POSITIVE LOGITS
    ipes
    0.28
    OWN
    0.27
     fucks
    0.26
    EB
    0.25
     scramble
    0.25
    æĿ¼
    0.25
    è¶ģ
    0.24
    æłĿ
    0.24
    ugar
    0.24
    è°±åĨĻ
    0.24
    Activations Density 0.471%

    No Known Activations