© 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. 30324
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Manus
    -0.27
     PY
    -0.26
    arden
    -0.25
     Darling
    -0.24
    olon
    -0.24
    peria
    -0.24
    Py
    -0.24
    GetX
    -0.24
    hm
    -0.23
     é»
    -0.23
    POSITIVE LOGITS
    å¿¿
    0.28
    åį¿
    0.27
    ests
    0.27
    äºı
    0.27
    -bind
    0.26
     profesional
    0.25
    ä¼ij
    0.25
    åıįæĦŁ
    0.24
     sideline
    0.24
    è´Ł
    0.24
    Activations Density 1.617%

    No Known Activations