© 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. 62054
    Prev
    Next
    INDEX
    Explanations

    infections and contamination

    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
    alin
    -0.10
    iben
    -0.10
    iros
    -0.10
    ÑĥÑī
    -0.09
    åıijçİ°éĹ®é¢ĺ
    -0.09
     Saul
    -0.09
    Glyph
    -0.08
    对ä»ĺ
    -0.08
    صاÙĦ
    -0.08
    /vnd
    -0.08
    POSITIVE LOGITS
    ilon
    0.09
    å»
    0.08
    åĩ«
    0.08
    å¸ĤæķĻèĤ²
    0.08
    åİ¢
    0.08
    ìĨ¡
    0.08
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
     ridden
    0.08
    iat
    0.08
    ered
    0.08
    Activations Density 0.364%

    No Known Activations