© 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. 62892
    Prev
    Next
    INDEX
    Explanations

    location or state of being

    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
    åľ¨ä¸ĢæĹģ
    -0.10
    åıijçĶŁåľ¨
    -0.09
    èĮĥ
    -0.09
    èĥ½åľ¨
    -0.09
    åŃĺåľ¨äºİ
    -0.09
     XB
    -0.08
    åĩºçİ°åľ¨
    -0.08
    饱
    -0.08
    esen
    -0.08
    _fg
    -0.08
    POSITIVE LOGITS
    çݯå¢ĥä¸Ń
    0.10
    å°½æĥħ
    0.10
    iera
    0.09
    acus
    0.09
    ä¼łåªĴ
    0.08
    éĻħ
    0.08
    ä¹Ŀå¹´
    0.08
    vertiser
    0.08
    illow
    0.08
    éĩijçīĮ
    0.08
    Activations Density 0.021%

    No Known Activations