© 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. 17658
    Prev
    Next
    INDEX
    Explanations

    numbers or ordinal suffixes

    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
    rush
    -0.09
    compat
    -0.09
    iden
    -0.09
    èĭ¥å¹²
    -0.09
    compatible
    -0.09
    __).
    -0.09
    erland
    -0.09
    åĩºåħ¥
    -0.08
    kaar
    -0.08
    ëĭĺ
    -0.08
    POSITIVE LOGITS
    teenth
    0.13
    ä¸į认è¯Ĩ
    0.09
    th
    0.09
    fold
    0.09
    è¯
    0.09
    äºĨ个
    0.08
    째
    0.08
    丧
    0.08
    å¯Łè§ī
    0.08
    riere
    0.08
    Activations Density 0.478%

    No Known Activations