© 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. 63444
    Prev
    Next
    INDEX
    Explanations

    New Year's holiday

    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
    æı´
    -0.12
    çī¹æ®ĬæĥħåĨµ
    -0.10
    åŀĭä¼ģä¸ļ
    -0.09
    æį¢åıĸ
    -0.09
    ntag
    -0.08
    .isOn
    -0.08
    èĢĺ
    -0.08
    uis
    -0.08
    ä¸įä¸ĭ
    -0.08
    okie
    -0.08
    POSITIVE LOGITS
    ê¹IJ
    0.11
    slt
    0.09
    stime
    0.09
    ä¼Ĭå§ĭ
    0.09
    sWith
    0.09
     Fellow
    0.09
    éĹ
    0.08
    estro
    0.08
    ĺ
    0.08
    åĴĮåıijå±ķ
    0.08
    Activations Density 0.007%

    No Known Activations