© 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. 55034
    Prev
    Next
    INDEX
    Explanations

    tires and wheels

    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
    èľĤ
    -0.10
    åŀ£
    -0.09
    çŃīåĢĻ
    -0.09
    pta
    -0.09
    ÑĢин
    -0.09
    çĩĥæĸĻ
    -0.09
     кÑĢÑĭÑĪ
    -0.09
    æĶ¶æ¬¾
    -0.09
    lei
    -0.08
    ãĤįãģĨ
    -0.08
    POSITIVE LOGITS
    è½®èĥİ
    0.15
    èĬ±çº¹
    0.10
    è¸ı
    0.09
    èµı
    0.09
    æīĺ
    0.08
    è¸ıå®ŀ
    0.08
     tread
    0.08
     tires
    0.08
    æīĽ
    0.08
     tyres
    0.08
    Activations Density 0.115%

    No Known Activations