© 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. 33158
    Prev
    Next
    INDEX
    Explanations

    Jekyll and Hyde, scientist

    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
    éĻ¬
    -0.09
    ÑĢаÑģÑĤ
    -0.09
    çĶij
    -0.09
    éĢīè´Ń
    -0.08
    æij§
    -0.08
    istr
    -0.08
    以éĺ²
    -0.08
    éĺĹ
    -0.08
    itura
    -0.08
    èĪĴéĢĤçļĦ
    -0.08
    POSITIVE LOGITS
    èĻ¹æ¡¥
    0.10
    atter
    0.08
    adian
    0.08
    gle
    0.08
    ä¸ĭ乡
    0.08
    é³ħ
    0.08
     latter
    0.08
    orer
    0.08
    Portal
    0.08
    æĭľ
    0.08
    Activations Density 0.004%

    No Known Activations