© 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. 31332
    Prev
    Next
    INDEX
    Explanations

    Judge Presiding

    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
    /from
    -0.11
    çĦ¶æĺ¯
    -0.10
    sov
    -0.10
    ities
    -0.10
    nda
    -0.09
    idades
    -0.09
    adies
    -0.09
    è¯Ŀ说
    -0.09
    kan
    -0.09
    iline
    -0.09
    POSITIVE LOGITS
    ess
    0.11
    ably
    0.11
    ëĭĺ
    0.10
    NEG
    0.09
    -offs
    0.09
    è¿Ļ个è¡Įä¸ļ
    0.09
    罡
    0.09
    hist
    0.09
    ication
    0.08
    esses
    0.08
    Activations Density 0.031%

    No Known Activations