© 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. 27988
    Prev
    Next
    INDEX
    Explanations

    game titles

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.11
    orch
    -0.09
    /mock
    -0.08
    éĵ±
    -0.08
    iku
    -0.08
    ès
    -0.08
    Compact
    -0.08
    æ§ģ
    -0.08
     TCL
    -0.08
    essim
    -0.08
    POSITIVE LOGITS
    åĩ»
    0.12
    å°½åı¯èĥ½
    0.10
    å°Ħåĩ»
    0.10
    å°Ħ
    0.10
    İ·
    0.10
    ç¿ģ
    0.09
    大æĪĺ
    0.09
    opi
    0.09
    ulous
    0.09
    zee
    0.09
    Activations Density 0.126%

    No Known Activations