© 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. 23124
    Prev
    Next
    INDEX
    Explanations

    Schneider, Apache, Winnipeg

    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
    ington
    -0.09
    ×ķת
    -0.08
    åĬ¾
    -0.08
    تج
    -0.08
    olo
    -0.08
    fully
    -0.07
    å¾ĺå¾Ĭ
    -0.07
    bridge
    -0.07
    andard
    -0.07
    nd
    -0.07
    POSITIVE LOGITS
    ../../../
    0.14
    rike
    0.10
    lops
    0.10
    ../../
    0.10
    usting
    0.10
    bing
    0.09
    idis
    0.09
    eam
    0.09
    ç¾İè²Į
    0.09
    çģ¯çģ«
    0.09
    Activations Density 0.060%

    No Known Activations