© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    child sexual abuse and molestation

    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
    ruc
    -0.09
    å¤ĸçķĮ
    -0.09
     pars
    -0.09
    yles
    -0.09
    æīŃ
    -0.09
    ĺ认
    -0.09
    ãĥĩãĥ³
    -0.09
    uming
    -0.08
    rops
    -0.08
     Covered
    -0.08
    POSITIVE LOGITS
    ish
    0.09
    åĴ«
    0.09
    åĦ¿ç«¥
    0.09
    溪
    0.08
    mel
    0.08
    éĢłåģĩ
    0.08
     Cres
    0.08
    è´º
    0.08
    ishly
    0.08
    ç¨ļ
    0.08
    Activations Density 0.016%

    No Known Activations