© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36137
    Prev
    Next
    INDEX
    Explanations

    condition

    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
    éĺ¡
    -0.10
    å¤ļå¤ļ
    -0.09
    makers
    -0.08
     counter
    -0.08
    uler
    -0.08
    缩çŁŃ
    -0.08
    ioc
    -0.08
    سÙĨØ©
    -0.08
     Loader
    -0.08
     squared
    -0.07
    POSITIVE LOGITS
     condition
    0.16
    èī¯å¥½
    0.14
    èī¯å¥½çļĦ
    0.14
    å®Į好
    0.14
    çĬ¶åĨµ
    0.14
    çĬ¶æĢģ
    0.13
     Condition
    0.13
    condition
    0.13
    Condition
    0.13
     CONDITION
    0.12
    Activations Density 0.066%

    No Known Activations