© 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. 30346
    Prev
    Next
    INDEX
    Explanations

    Wales

    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
     Tail
    -0.31
     tail
    -0.29
    `s
    -0.28
    tail
    -0.27
    åĢĴåľ¨
    -0.27
     femin
    -0.27
    Tail
    -0.27
    ä¸į对
    -0.26
     Lod
    -0.25
    .prop
    -0.25
    POSITIVE LOGITS
    monic
    0.26
    ä¸ĢæĹı
    0.25
    å°¬
    0.24
     câ
    0.24
    ()"↵
    0.24
    伺
    0.24
    车èģĶç½ij
    0.24
    precated
    0.24
    æĻĥ
    0.23
    vak
    0.23
    Activations Density 2.619%

    No Known Activations