© 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. 31649
    Prev
    Next
    INDEX
    Explanations

    report of cases

    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
    åıªèĥ½è¯´
    -0.10
    åģļ强
    -0.09
    Unnamed
    -0.09
    ossa
    -0.09
    èµ°åIJij
    -0.09
    çķĻä¸ĭäºĨ
    -0.09
    è¡Ķ
    -0.09
    ÑħодиÑĤÑĮ
    -0.09
    Browsable
    -0.09
    ä¸ĭæ²ī
    -0.09
    POSITIVE LOGITS
     cases
    0.15
    çĹħä¾ĭ
    0.15
     case
    0.14
    æ¡Īä¾ĭ
    0.14
    cases
    0.12
     Cases
    0.12
    æŃ»äº¡
    0.11
    case
    0.11
    ä¸ĬæĬ¥
    0.10
     Case
    0.10
    Activations Density 0.375%

    No Known Activations