© 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. 50175
    Prev
    Next
    INDEX
    Explanations

    primitive

    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
    ingly
    -0.13
    oons
    -0.09
    ings
    -0.08
    ë¹Ļ
    -0.08
    å¹³åİŁ
    -0.08
    ÑĥÑĩа
    -0.08
    aina
    -0.08
    ification
    -0.08
    loe
    -0.08
    åĿ¡
    -0.08
    POSITIVE LOGITS
    ity
    0.09
    /native
    0.09
    åijĬè¯ī大家
    0.09
    踪
    0.09
    otta
    0.09
    -looking
    0.08
    ç±į
    0.08
    åŃ³
    0.08
    å¼Ģå¿ĥ
    0.08
    æī¼
    0.08
    Activations Density 0.008%

    No Known Activations