© 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. 48211
    Prev
    Next
    INDEX
    Explanations

    Dow Jones Industrial Average

    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
    bread
    -0.09
    pé
    -0.09
    亲æĥħ
    -0.09
    亲è¿ij
    -0.09
    BUR
    -0.09
     chance
    -0.08
    éŃħ
    -0.08
    çįł
    -0.08
    wner
    -0.08
     Chance
    -0.08
    POSITIVE LOGITS
    çĢijå¸ĥ
    0.09
    èĢģèĻİ
    0.09
    宿
    0.09
    åĺĢ
    0.09
    è¿Ļ个人
    0.09
    èĻ±
    0.08
    åŀĥåľ¾æ¡¶
    0.08
     наÑĢ
    0.08
    ä¸Ĭä¸ĭ游
    0.08
    æĬĬ她
    0.08
    Activations Density 0.004%

    No Known Activations