© 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. 33485
    Prev
    Next
    INDEX
    Explanations

    tails

    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
    æīĵåħ¥
    -0.09
    æĸ¥
    -0.09
    楹
    -0.08
    äºĨå¤ļå°ij
    -0.08
    æ°´åĩĨ
    -0.08
    å¨ĺ家
    -0.08
    setType
    -0.08
     CFR
    -0.08
    éĽ³
    -0.08
     conc
    -0.08
    POSITIVE LOGITS
    tail
    0.10
    è¾į
    0.10
    å°¾
    0.09
    ÆĶ
    0.09
     avis
    0.09
    ä¹Łä¸įæķ¢
    0.09
     tails
    0.09
     tail
    0.09
    èĬĴ
    0.08
    æįħ
    0.08
    Activations Density 0.008%

    No Known Activations