© 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. 29451
    Prev
    Next
    INDEX
    Explanations

    F

    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
    rez
    -0.28
    qing
    -0.25
     Rid
    -0.25
    rats
    -0.25
    æĬĹæĪĺ
    -0.25
     species
    -0.24
    pac
    -0.24
     rats
    -0.24
     directives
    -0.24
    max
    -0.24
    POSITIVE LOGITS
    åĽłåľ°
    0.29
    ABCDEFGHIJKLMNOP
    0.26
    éĥ¨åī¯
    0.25
     Jaune
    0.25
    å°±æĬĬ
    0.25
    ogenerated
    0.24
     :↵↵↵↵
    0.24
    éĥ½è®¤ä¸º
    0.24
    éĢģä¸Ĭ
    0.24
    éĵ³
    0.24
    Activations Density 3.079%

    No Known Activations