© 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. 9131
    Prev
    Next
    INDEX
    Explanations

    claw or claws

    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
    æĸĻ
    -0.09
    -weight
    -0.09
    顾éĹ®
    -0.09
    ä»»ä½ķä¸Ģ个
    -0.09
    weight
    -0.08
    åIJ¹
    -0.08
    åľ¬
    -0.08
    å¿ĥåĬ¨
    -0.08
    èĢIJå¿ĥ
    -0.08
     дол
    -0.08
    POSITIVE LOGITS
    çĪª
    0.17
     claws
    0.12
     Claw
    0.12
     claw
    0.11
    çīĻ齿
    0.10
    çĭ°
    0.10
    åľ¨èģĮ
    0.10
    夷
    0.09
    强大
    0.09
    森
    0.09
    Activations Density 0.073%

    No Known Activations