© 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. 22-TRANSCODER-HP
    7. 129072
    Prev
    Next
    INDEX
    Explanations

    on/in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    omination
    -0.34
    ouncer
    -0.30
    æĢİä¹Īåģļ
    -0.27
    ä¹Łæľīå¾Īå¤ļ
    -0.27
    lsi
    -0.26
    gett
    -0.25
    è¶Ĭæĺ¯
    -0.25
    arb
    -0.24
     Cobb
    -0.24
    velte
    -0.24
    POSITIVE LOGITS
    ủng
    0.25
    anko
    0.25
     vra
    0.24
    ycz
    0.24
    lew
    0.24
    (shared
    0.24
    å·¥ä½ľæĬ¥åijĬ
    0.24
    atial
    0.23
    åĬ
    0.23
    åħ±äº«
    0.23
    Activations Density 0.010%

    No Known Activations