© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20129
    Prev
    Next
    INDEX
    Explanations

    up or down movement

    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
    éĢĢç¨İ
    -0.08
     dare
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
    ä¹łè¿ij
    -0.08
    cert
    -0.08
    utom
    -0.08
    ализ
    -0.07
    PCR
    -0.07
     successors
    -0.07
     каÑĩ
    -0.07
    POSITIVE LOGITS
    ingly
    0.17
    èĢĮåĩº
    0.12
    lander
    0.11
    æ¶Įåħ¥
    0.10
    baugh
    0.10
    isel
    0.10
    æĶĢåįĩ
    0.10
    ä¸įå·²
    0.10
    椽
    0.10
    æĹłæ¯Ķ
    0.09
    Activations Density 0.014%

    No Known Activations