© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38076
    Prev
    Next
    INDEX
    Explanations

    zoom lens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹£
    -0.10
    illon
    -0.10
    åĿ¨
    -0.09
     Pell
    -0.09
    oger
    -0.09
    åłĤ
    -0.09
    æ½®
    -0.09
    åįij
    -0.08
    ower
    -0.08
    è¡£
    -0.08
    POSITIVE LOGITS
    çľ¼åħī
    0.09
    .cleaned
    0.09
    strup
    0.09
    浦
    0.08
    å®īå¨ľ
    0.08
    åĩºåħ¥
    0.08
    éķľå¤´
    0.08
    RunWith
    0.08
    æ¦Ĥæĭ¬
    0.08
     Dah
    0.08
    Activations Density 0.016%

    No Known Activations