© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7991
    Prev
    Next
    INDEX
    Explanations

    burn or born endings

    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
    мел
    -0.10
    åĽ¹
    -0.09
    rot
    -0.09
    pile
    -0.09
    обоÑĢ
    -0.08
    å¤ļä¹Ī
    -0.08
    çĸ¯çĭĤ
    -0.08
    quito
    -0.08
    rove
    -0.08
    ç¬Ī
    -0.08
    POSITIVE LOGITS
    shire
    0.11
    Ñĩик
    0.10
    iam
    0.10
    å·¥ä½ľä½ľé£İ
    0.09
    auc
    0.09
    edo
    0.09
    鸽
    0.09
    åıijå±ķ空éĹ´
    0.09
    lius
    0.09
    åı£æ°´
    0.09
    Activations Density 0.021%

    No Known Activations