© 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. 27502
    Prev
    Next
    INDEX
    Explanations

    for up to, for potential, for deals

    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
    æłĩéħį
    -0.09
    æıIJåĢ¡
    -0.09
    -pill
    -0.09
    è«
    -0.09
    åħ¼
    -0.09
    伸æīĭ
    -0.08
     Brush
    -0.08
    åĻİ
    -0.08
    èŁ¹
    -0.08
    以çĤº
    -0.08
    POSITIVE LOGITS
    sey
    0.10
    HEL
    0.09
    è´¢
    0.08
    派驻
    0.08
    çĮľ
    0.08
    åľ°åŁŁ
    0.08
    seys
    0.08
    ç»İ
    0.08
     Nobel
    0.08
    èĤĦ
    0.08
    Activations Density 0.133%

    No Known Activations