© 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. 62254
    Prev
    Next
    INDEX
    Explanations

    sp followed by specific endings (okes, itting, as, acific, etc.)

    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
    çĦ¶æĺ¯
    -0.09
    绩
    -0.09
    imony
    -0.09
    æĭĬ
    -0.09
    eger
    -0.09
    gence
    -0.09
    åĩºéŨ
    -0.08
    OUS
    -0.08
    ç
    -0.08
    unting
    -0.08
    POSITIVE LOGITS
    .sp
    0.10
    okes
    0.09
    -sp
    0.09
    ghan
    0.09
    *sp
    0.09
    sp
    0.09
    spread
    0.09
    äºĨä¸Ģ
    0.09
    åĬ£
    0.09
     ÑģамоÑģÑĤоÑı
    0.09
    Activations Density 0.032%

    No Known Activations