© 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. 63568
    Prev
    Next
    INDEX
    Explanations

    organized crime syndicates

    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
    FetchRequest
    -0.11
    å¹ħ度
    -0.10
    åħij
    -0.10
    _DUMP
    -0.10
    amac
    -0.09
    æŀ£
    -0.09
    åłĥ
    -0.08
    çĻ½é©¬
    -0.08
    fläche
    -0.08
    ä¼ļåĩºçİ°
    -0.08
    POSITIVE LOGITS
    ipel
    0.09
    ä¸įåħĭ
    0.09
    .inject
    0.08
    orbit
    0.08
    èĩ³æĸ¼
    0.08
    èĩ³äºİ
    0.08
    ç¡ķ
    0.08
    ãĤ¿ãĤ¤
    0.08
    ãģ¤ãģĭ
    0.08
    åij±
    0.08
    Activations Density 0.009%

    No Known Activations