© 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. 22821
    Prev
    Next
    INDEX
    Explanations

    year/month/day

    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
    éĢŀ
    -0.09
    åĮ¡
    -0.09
    å½ĵæŶ
    -0.08
    å¸
    -0.08
    äºĴåĬ©
    -0.08
    arry
    -0.08
    -bars
    -0.08
    å½ĵæŶçļĦ
    -0.08
     herr
    -0.08
    è³¢
    -0.08
    POSITIVE LOGITS
    äh
    0.08
    semester
    0.08
    aley
    0.08
    åľ¨è¿Ļç§į
    0.08
    FRAME
    0.08
    kos
    0.08
    IFA
    0.08
    paragus
    0.08
    _LOGGER
    0.08
    ä¸Ńç§ĭ
    0.08
    Activations Density 0.090%

    No Known Activations