© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    field names

    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
    ä¸ľè¥¿
    -0.08
    AGE
    -0.08
    éģĵ
    -0.08
    èĤ¤
    -0.08
    idade
    -0.08
    çĵľ
    -0.08
    æ·±
    -0.08
    .sep
    -0.08
    izado
    -0.08
    è´¢å¯Į
    -0.08
    POSITIVE LOGITS
     Fields
    0.16
    (Field
    0.15
     fields
    0.15
     Field
    0.15
    .Field
    0.14
     field
    0.14
    (fields
    0.14
    \Field
    0.13
    .fields
    0.13
     getField
    0.13
    Activations Density 0.212%

    No Known Activations