© 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. 54246
    Prev
    Next
    INDEX
    Explanations

    describing a setting

    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
    ets
    -0.10
    ilon
    -0.09
    绪
    -0.08
    ìĦ¸ìļĶ
    -0.08
    ç½®æį¢
    -0.08
    heid
    -0.08
    çīį
    -0.08
    µ
    -0.08
    osten
    -0.08
    è½½
    -0.07
    POSITIVE LOGITS
    è´
    0.11
    ä½ķå¿ħ
    0.10
    iful
    0.09
    âĵĺ
    0.09
    regs
    0.09
    erus
    0.09
    æŃ¦ä¾ł
    0.09
    毡
    0.09
    çĶµåı°
    0.09
    SETTING
    0.09
    Activations Density 0.022%

    No Known Activations