© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62202
    Prev
    Next
    INDEX
    Explanations

    hook and loop

    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
     Luz
    -0.11
     liá»ĩu
    -0.10
    èķī
    -0.10
    éĺ¡
    -0.09
    è¯Ł
    -0.09
    uous
    -0.08
    lı
    -0.08
    æIJģ
    -0.08
    ë£Į
    -0.08
    cape
    -0.08
    POSITIVE LOGITS
    rete
    0.10
    edList
    0.10
    tail
    0.09
    éĴ©
    0.09
    ../../../
    0.09
    å½ĵãģŁãĤĬ
    0.09
    ertz
    0.09
    tails
    0.09
    achu
    0.08
    sett
    0.08
    Activations Density 0.015%

    No Known Activations