© 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. 19127
    Prev
    Next
    INDEX
    Explanations

    failed followed by a problem

    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
    dur
    -0.09
    åħ¶æīĢ
    -0.09
    تÙĤ
    -0.09
    صÙģ
    -0.08
    auses
    -0.08
    à¹ĥà¸Ī
    -0.08
     Either
    -0.08
    izations
    -0.08
    _FD
    -0.08
    Ñģад
    -0.08
    POSITIVE LOGITS
    landers
    0.11
    æİ¥çĿĢ
    0.10
    äºĨå¤ļå°ij
    0.09
    ç²¾åĩĨ
    0.09
     attempt
    0.09
    å¿»
    0.09
    attempt
    0.09
    éļıåIJİ
    0.09
    ç²¾èĭ±
    0.09
    顶å±Ĥ设计
    0.09
    Activations Density 0.017%

    No Known Activations