© 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. 54456
    Prev
    Next
    INDEX
    Explanations

    failed attempt experiment

    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
    æŃ£åĢ¼
    -0.09
    æ·±èĢķ
    -0.09
    è¦ģç´§
    -0.09
    佬
    -0.09
    ä¸Ģæīĭ
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.09
    æŃ£åľ¨
    -0.08
    çĭİ
    -0.08
    _OCC
    -0.08
    bian
    -0.08
    POSITIVE LOGITS
    失败
    0.20
    å°Ŀè¯ķ
    0.17
     attempt
    0.16
     failed
    0.15
    è¯ķåĽ¾
    0.15
    failed
    0.14
     Failed
    0.14
     attempts
    0.13
    Attempt
    0.13
    æľªèĥ½
    0.13
    Activations Density 0.270%

    No Known Activations