© 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. 49019
    Prev
    Next
    INDEX
    Explanations

    to the

    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
    Hip
    -0.10
    æµģæ°´
    -0.10
    åħ±
    -0.09
    æѧ
    -0.09
    imet
    -0.09
    æŃ¥ä¼IJ
    -0.09
    _rq
    -0.08
    igli
    -0.08
    è´´
    -0.08
    缸å½ĵ
    -0.08
    POSITIVE LOGITS
    ä¸ĬåįĪ
    0.09
    emple
    0.09
    å°ıå°ıçļĦ
    0.09
    åĵŃäºĨ
    0.09
    adge
    0.08
     Rh
    0.08
    å½°
    0.08
    è§ĤæľĽ
    0.08
     rh
    0.08
    åıijè¨Ģ人
    0.08
    Activations Density 0.013%

    No Known Activations