© 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. 7259
    Prev
    Next
    INDEX
    Explanations

    client/server context

    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
    antis
    -0.09
    å®īä¿Ŀ
    -0.09
    mour
    -0.09
    ding
    -0.09
    äºĭåħĪ
    -0.09
    éľ²åĩº
    -0.09
    çĪ¸å¦Ī
    -0.09
    棰
    -0.09
    åīįæīĢ
    -0.08
    è·Łä½ł
    -0.08
    POSITIVE LOGITS
    -side
    0.10
    Ñĥд
    0.10
    (Client
    0.09
    æ¡Ħ
    0.09
    aur
    0.08
    端
    0.08
    olina
    0.08
    /client
    0.08
    åįĴ
    0.08
    -library
    0.08
    Activations Density 0.124%

    No Known Activations