© 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. 53580
    Prev
    Next
    INDEX
    Explanations

    spin truth news propaganda

    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
    éĶĦ
    -0.10
    unities
    -0.09
    ä»ķ
    -0.09
    å¤Ļ
    -0.09
    åIJĮåŁİ
    -0.09
    æ¡Ī
    -0.09
    æĥ©
    -0.09
    _probe
    -0.09
    讫
    -0.09
    éķ¢
    -0.08
    POSITIVE LOGITS
     port
    0.10
    çĽ¸ä¿¡å¤§å®¶
    0.09
    chemy
    0.09
    itzer
    0.09
    åıĺå½¢
    0.09
    ç©¿æ¢Ń
    0.09
    5
    0.09
    2
    0.08
    åıĤè°ĭ
    0.08
    9
    0.08
    Activations Density 0.067%

    No Known Activations