© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    possibility and questions of possibility

    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
    çļĦå¿ĥæĥħ
    -0.09
    æĹłå£°
    -0.09
    éĩĬ
    -0.09
    eltas
    -0.09
    æī¾ä¸įåĪ°
    -0.08
    éļ¾åıĹ
    -0.08
    har
    -0.08
    ader
    -0.08
    redo
    -0.08
    主ä½ĵ
    -0.08
    POSITIVE LOGITS
    åı¯èĥ½æĢ§
    0.26
     possibility
    0.25
    çļĦåı¯èĥ½æĢ§
    0.24
     possibilities
    0.22
     возможноÑģÑĤÑĮ
    0.20
     possibilit
    0.18
    æľīåı¯èĥ½
    0.18
     possibilitÃł
    0.18
     possibilité
    0.17
     возможноÑģÑĤи
    0.16
    Activations Density 0.266%

    No Known Activations