© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22347
    Prev
    Next
    INDEX
    Explanations

    software development and programming

    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
    _pins
    -0.09
    çĸijéļ¾
    -0.09
    ä¸ĵ
    -0.08
    æ²»çIJĨä½ĵç³»
    -0.08
    oris
    -0.08
    æĬµ
    -0.08
    9
    -0.08
    æIJ¦
    -0.08
    6
    -0.08
    ileges
    -0.08
    POSITIVE LOGITS
     McCabe
    0.11
    çĤĴ
    0.10
    éĽī
    0.09
    _mC
    0.09
    SPAN
    0.09
    åı¸
    0.09
     Hose
    0.09
    跨度
    0.09
    Lewis
    0.08
     bekannt
    0.08
    Activations Density 0.415%

    No Known Activations