© 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. 31263
    Prev
    Next
    INDEX
    Explanations

    Jeep, Colorado, Cruiser, Ranger, Durango

    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
    书é¦Ļ
    -0.09
    微微
    -0.09
    å½Ĺ
    -0.09
     дог
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    ç¿©
    -0.09
    opsis
    -0.09
    å¿ĥè¡Ģ
    -0.09
    ç»ıéªĮåĢ¼
    -0.09
    鲸
    -0.08
    POSITIVE LOGITS
    è¶Ĭéĩİ
    0.11
    åѦä¼ļ
    0.09
    bilt
    0.09
     jeep
    0.08
     ranger
    0.08
    寨
    0.08
     Chew
    0.08
    Spoiler
    0.08
     Ranger
    0.08
    .shtml
    0.08
    Activations Density 0.024%

    No Known Activations