© 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. 4471
    Prev
    Next
    INDEX
    Explanations

    valued at

    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
    DDL
    -0.10
    èĽ¾
    -0.09
    é«ĺ强度
    -0.09
    æ³±
    -0.09
    å²·
    -0.09
    æµģ泪
    -0.09
    æĢ§åij½
    -0.08
    âĨĹ
    -0.08
    ç¥Ł
    -0.08
    ãĥ¼ãĤ¿
    -0.08
    POSITIVE LOGITS
    omm
    0.10
    ellers
    0.08
    å¯Ĵ
    0.08
     Ùħد
    0.08
    转移åĪ°
    0.08
    æĭ¾
    0.08
    _utc
    0.08
    _INF
    0.08
    ç¥ķ
    0.08
     DIG
    0.08
    Activations Density 0.030%

    No Known Activations