© 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. 17663
    Prev
    Next
    INDEX
    Explanations

    career milestones

    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
    åı²æĸĻ
    -0.09
    楸
    -0.09
    ï¼Īç¬ij
    -0.08
    å¨
    -0.08
    icer
    -0.08
    æĤ¦
    -0.08
    æĸĩ娱
    -0.08
    chem
    -0.08
    æĸĩçĮ®
    -0.08
    æĪijåĴĮ
    -0.08
    POSITIVE LOGITS
    èĩªåľ¨
    0.10
    è·¨çķĮ
    0.10
    èĽ°
    0.10
    常
    0.09
    èĩªå¦Ĥ
    0.09
    å¡ijéĢł
    0.09
    常常
    0.09
    åĽ½éĻħåIJĪä½ľ
    0.09
    è°¦
    0.08
    è¡Įç¨ĭ
    0.08
    Activations Density 0.217%

    No Known Activations