© 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. 26545
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
    æľĢ容æĺĵ
    -0.09
    æĢħ
    -0.09
    è¿ĺä¸įæĺ¯
    -0.08
    æģ£
    -0.08
    æľĢå¿«
    -0.08
    ä¸įæĪIJ
    -0.08
    çĢij
    -0.08
    æ¦Ħ
    -0.08
    dro
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
    çħ§
    0.10
    heid
    0.10
    bens
    0.09
    æ»ķ
    0.09
    _tid
    0.09
    бед
    0.09
    иÑĤеÑĤ
    0.09
    éĢ´
    0.09
    æ¿
    0.09
    LEMENT
    0.09
    Activations Density 0.008%

    No Known Activations