© 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. 52758
    Prev
    Next
    INDEX
    Explanations

    recommendation or advice

    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
    elig
    -0.11
    æĤłæĤł
    -0.09
    elah
    -0.09
    bnb
    -0.09
    coin
    -0.09
    gger
    -0.09
    ud
    -0.09
    cul
    -0.09
    pers
    -0.09
    lain
    -0.09
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.10
    ISE
    0.10
    ãĤĭãģĵãģ¨ãģĮ
    0.10
    stration
    0.09
    tpl
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    or
    0.09
    .urlopen
    0.08
    ç¬Ħ
    0.08
    tl
    0.08
    Activations Density 0.018%

    No Known Activations