© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    automotive brands and HTML documents

    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
    æ²®
    -0.11
    ly
    -0.10
    stoff
    -0.10
    ¶
    -0.09
    atak
    -0.09
    æ³½
    -0.08
    éļį
    -0.08
    æĢ§çĸ¾çĹħ
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    ed
    -0.08
    POSITIVE LOGITS
    æ³ķ人
    0.09
    dle
    0.09
    oret
    0.09
     Scarborough
    0.08
    åıĹä¼Ĺ
    0.08
    ov
    0.08
    è§ī
    0.08
    illon
    0.08
    IDD
    0.08
    åĨľä¸ļ大åѦ
    0.08
    Activations Density 0.007%

    No Known Activations