© 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. 30148
    Prev
    Next
    INDEX
    Explanations

    fundamental components

    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
    primitive
    -0.29
    indre
    -0.28
     uniform
    -0.27
    åĩĮ
    -0.27
    spiel
    -0.25
    Primitive
    -0.25
     primitive
    -0.25
     ìŀIJìľł
    -0.25
    fires
    -0.25
    ivement
    -0.25
    POSITIVE LOGITS
     UserManager
    0.28
    anke
    0.28
    è¡¡éĺ³
    0.27
    pear
    0.27
    Dest
    0.26
    å®ıè§Ĥ
    0.25
     Tanner
    0.24
    è°ı
    0.24
     pear
    0.24
     Ward
    0.23
    Activations Density 3.056%

    No Known Activations