© 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. 48530
    Prev
    Next
    INDEX
    Explanations

    translation, identification, peptide, study

    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
     OMIT
    -0.09
    龸
    -0.08
     scalar
    -0.08
     Folk
    -0.08
    inel
    -0.08
    jur
    -0.08
    èݽ
    -0.08
    кал
    -0.08
    ias
    -0.08
    NECT
    -0.08
    POSITIVE LOGITS
    éģĹ
    0.11
    åİŁèijĹ
    0.11
    被èªī
    0.11
    éĴĹ
    0.11
    åİŁæĸĩ
    0.10
    大å®Ĺ
    0.09
    éªĬ
    0.09
    è°ĭ
    0.09
    ä¹ĺ车
    0.09
    绿èī²éĢļéģĵ
    0.09
    Activations Density 0.084%

    No Known Activations