© 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. 7176
    Prev
    Next
    INDEX
    Explanations

    Hopkins University

    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
    wares
    -0.11
    istic
    -0.11
    charm
    -0.10
    ios
    -0.09
    istically
    -0.09
    zung
    -0.08
    entine
    -0.08
    çĶŁæķĪ
    -0.08
    ä¸Ŀ绸ä¹ĭè·¯
    -0.08
    untime
    -0.08
    POSITIVE LOGITS
    eler
    0.10
    yon
    0.09
    edList
    0.09
    人士
    0.09
    /J
    0.08
    _itr
    0.08
    Assets
    0.08
    äºĭå®ŀä¸Ĭ
    0.08
    èĬ
    0.08
    ect
    0.08
    Activations Density 0.017%

    No Known Activations