© 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. 39863
    Prev
    Next
    INDEX
    Explanations

    intense or intensely

    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
    大大æıIJé«ĺ
    -0.09
    avig
    -0.09
    무
    -0.08
    atr
    -0.08
    fone
    -0.08
    alysis
    -0.08
    大大
    -0.08
    ãģªãĤĵãģ¨
    -0.08
    reo
    -0.08
    recht
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    çļĦ缮åħī
    0.11
    OMET
    0.11
    ingly
    0.10
    ément
    0.10
    ively
    0.10
    æĥ³çŁ¥éģĵ
    0.10
    çĤ½
    0.10
    æĹłæ¯Ķ
    0.10
    åı¸é©¬
    0.09
    Activations Density 0.018%

    No Known Activations