© 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. 18955
    Prev
    Next
    INDEX
    Explanations

    signs and evidence of

    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
    нÑĤ
    -0.10
    éļľ
    -0.10
    æĹłäºº
    -0.09
    lad
    -0.09
    çµ®
    -0.09
    çŁŃçŁŃ
    -0.09
     Wish
    -0.08
    æ¸IJ
    -0.08
    genome
    -0.08
    led
    -0.08
    POSITIVE LOGITS
    迹象
    0.22
     signs
    0.16
     evidence
    0.15
    Evidence
    0.14
     Evidence
    0.14
    è¯ģæį®
    0.14
     dấu
    0.14
    çĹķ迹
    0.14
     Signs
    0.13
    身影
    0.13
    Activations Density 0.110%

    No Known Activations