© 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. 9686
    Prev
    Next
    INDEX
    Explanations

    code and license templates

    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
    åĪ°è´¦
    -0.09
    çĨĺ
    -0.08
    è´²
    -0.08
    åľ¨å¤ĸ
    -0.08
    ICO
    -0.08
    Spoiler
    -0.07
     ,
    -0.07
     Lorem
    -0.07
    uber
    -0.07
    ç»ıæŁ¥
    -0.07
    POSITIVE LOGITS
    å§Ĭ妹
    0.10
    å§IJ妹
    0.09
    ãĥijãĥijæ´»
    0.09
     civilian
    0.09
    VILLE
    0.09
    umped
    0.09
    å²Ĭ
    0.09
    ificate
    0.09
    å¼Ń
    0.09
    å§Ĵ
    0.09
    Activations Density 0.073%

    No Known Activations