© 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. 56722
    Prev
    Next
    INDEX
    Explanations

    exoplanets and habitability

    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
    èīĩ
    -0.10
    ãĤīãģı
    -0.10
    æłī
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
     magna
    -0.09
    éģij
    -0.09
    汽车产ä¸ļ
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    ship
    -0.08
    _EXPORT
    -0.08
    POSITIVE LOGITS
     habit
    0.09
    å®ľå±ħ
    0.09
    ä¹ĭå¤ĸ
    0.08
    衬
    0.08
    xico
    0.08
    æķĻèĤ²
    0.08
    å©Ĩ
    0.08
     Courier
    0.08
    份
    0.08
     ÑģаÑħаÑĢ
    0.08
    Activations Density 0.016%

    No Known Activations