© 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. 49040
    Prev
    Next
    INDEX
    Explanations

    harmful effects and substances

    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
    å¦į
    -0.10
    okes
    -0.10
    glass
    -0.09
    /Sub
    -0.09
    chas
    -0.09
    æ²IJ
    -0.09
    ointed
    -0.08
    glas
    -0.08
    usz
    -0.08
    æ´Ĺ
    -0.08
    POSITIVE LOGITS
    7
    0.09
    1
    0.09
    5
    0.09
    ä»ħä»ħ
    0.09
    alo
    0.09
    4
    0.09
    6
    0.09
    æŶæŶ
    0.09
    0
    0.09
    8
    0.09
    Activations Density 0.067%

    No Known Activations