© 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. 21428
    Prev
    Next
    INDEX
    Explanations

    upgrade or upgraded

    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
    å´
    -0.10
    rift
    -0.09
    åĩºåľº
    -0.09
    ç¿ģ
    -0.08
    /operators
    -0.08
     обÑĢаÑī
    -0.08
    ugen
    -0.08
    èĽ
    -0.08
    аÑĢÑĮ
    -0.08
    arem
    -0.08
    POSITIVE LOGITS
    åĪ°è¿ĻéĩĮ
    0.11
    åĪ°æĿ¥
    0.11
    åĪ°
    0.10
    åĪ°äºĨ
    0.09
     tỼi
    0.09
     Respons
    0.09
    温馨æıIJ示
    0.09
    å°¤åħ¶
    0.09
    èĩ³æѤ
    0.09
    èĩ³
    0.09
    Activations Density 0.052%

    No Known Activations