© 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. 31320
    Prev
    Next
    INDEX
    Explanations

    be able to

    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
    åĽ°æĥij
    -0.11
    ä¸Ģä¸ĸ
    -0.09
    èĪĶ
    -0.09
    æīįç®Ĺ
    -0.09
    æľªæĿ¥çļĦ
    -0.09
    å·²ç»ıæĺ¯
    -0.09
    éĵĬ
    -0.09
    顶å°ĸ
    -0.08
    atetime
    -0.08
    ·»
    -0.08
    POSITIVE LOGITS
     able
    0.17
     ability
    0.17
    èĥ½å¤Ł
    0.14
    Ability
    0.12
    èĥ½å¤ł
    0.11
     Ability
    0.11
    èĥ½æĬĬ
    0.11
    èĥ½åľ¨
    0.11
    èĥ½å¤Łåľ¨
    0.11
    èĥ½
    0.11
    Activations Density 0.106%

    No Known Activations