© 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. 29392
    Prev
    Next
    INDEX
    Explanations

    vote

    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
    Not in Any Lists

    No Comments

    Negative Logits
    berry
    -0.29
     berry
    -0.29
     baff
    -0.26
     Berry
    -0.26
    ä¸Ģ举
    -0.25
    ɣ
    -0.25
    ׾×ij
    -0.25
    ta
    -0.24
    è¡Į为
    -0.24
    Ãłi
    -0.24
    POSITIVE LOGITS
    ç¬ķ
    0.26
     Samp
    0.26
    ä¸įä¿¡
    0.26
    åħŃ大
    0.25
     flyer
    0.25
    Dream
    0.25
     Kod
    0.24
    enor
    0.24
     scheme
    0.24
    æĿľåħ°
    0.24
    Activations Density 1.410%

    No Known Activations