© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    was Kramer’s

    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
    åĦĨ
    -0.09
    ä¼´éļı
    -0.08
    åĬ¨æĦŁ
    -0.08
    缴éĶĢ
    -0.08
    erton
    -0.08
    paren
    -0.08
    åŀĽ
    -0.08
    çī¢åĽº
    -0.08
     Recomm
    -0.08
    çĽ²
    -0.08
    POSITIVE LOGITS
    cej
    0.10
    agn
    0.10
    ä¹ĭä½Ļ
    0.09
    è¿ľç¦»
    0.09
    -rad
    0.09
    adel
    0.08
    äºİæѤ
    0.08
    æĽ²æĬĺ
    0.08
    gin
    0.08
    chem
    0.08
    Activations Density 0.163%

    No Known Activations