© 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. 23322
    Prev
    Next
    INDEX
    Explanations

    toxic

    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
    ymmetric
    -0.09
    zelf
    -0.09
    licative
    -0.09
    atically
    -0.09
    nger
    -0.09
    atical
    -0.09
    owing
    -0.08
    iard
    -0.08
    oret
    -0.08
    ierce
    -0.08
    POSITIVE LOGITS
    å¤ł
    0.12
    oling
    0.11
    ening
    0.11
    æĹłæ¯Ķ
    0.11
    ities
    0.11
    ité
    0.11
    è¦ģæĬĬ
    0.11
    è¯ĥ
    0.10
    -minded
    0.10
    emia
    0.10
    Activations Density 0.022%

    No Known Activations