© 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. 36029
    Prev
    Next
    INDEX
    Explanations

    Inv/Conf prefixes

    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
    hood
    -0.16
    keit
    -0.11
    hip
    -0.10
    tempts
    -0.10
    ÙĦاÙĨ
    -0.10
    ugh
    -0.10
    shal
    -0.10
    oft
    -0.09
    æŃ¥æŃ¥
    -0.09
    usercontent
    -0.09
    POSITIVE LOGITS
    el
    0.10
    il
    0.09
    SYS
    0.09
    Ùij
    0.09
    äºĨäºĽ
    0.09
    esz
    0.09
    人士
    0.08
    ert
    0.08
    ed
    0.08
    çģ¾åĮº
    0.08
    Activations Density 0.062%

    No Known Activations