© 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. 62592
    Prev
    Next
    INDEX
    Explanations

    valentine's 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
    éªĪ
    -0.09
    ä»Ĩ
    -0.09
    CancelButton
    -0.09
    è§Ĩ线
    -0.09
    åĵģä½į
    -0.09
    FRING
    -0.08
    éķľå¤´
    -0.08
    orage
    -0.08
    æ¸Ķ
    -0.08
    utc
    -0.08
    POSITIVE LOGITS
    æ¡£
    0.10
    tion
    0.09
    æĪij对
    0.09
    åĨĮ
    0.09
    ism
    0.09
    æĶ»åĬ¿
    0.09
    éĴ¿
    0.09
    izing
    0.08
    adt
    0.08
    èľļ
    0.08
    Activations Density 0.002%

    No Known Activations