© 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. 10557
    Prev
    Next
    INDEX
    Explanations

    go run

    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
    éĴµ
    -0.10
    amarin
    -0.09
    åħ»èĢģéĩij
    -0.09
    yr
    -0.09
    纶
    -0.09
    richt
    -0.09
    èķī
    -0.08
    è¢ħ
    -0.08
    èĭ¦ç¬ij
    -0.08
    stab
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.13
    thic
    0.10
    itre
    0.10
    ffer
    0.09
    ðŁı¼
    0.09
    æ¶Įçİ°
    0.09
    ä¸ĭæīĭ
    0.08
    irth
    0.08
    otive
    0.08
    allon
    0.08
    Activations Density 0.055%

    No Known Activations