© 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. 49076
    Prev
    Next
    INDEX
    Explanations

    misinformation and misconceptions

    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
    jing
    -0.09
    MEM
    -0.09
     Hind
    -0.09
    okes
    -0.09
    ols
    -0.09
    oves
    -0.09
    zac
    -0.08
    失æķĪ
    -0.08
    asy
    -0.08
     Äijâu
    -0.08
    POSITIVE LOGITS
    ellaneous
    0.10
    è§Į
    0.10
    sWith
    0.09
    认为
    0.09
     notions
    0.09
    æĥ³æ³ķ
    0.09
    éķŃ
    0.09
    sm
    0.09
    ockets
    0.09
    صÙĬب
    0.09
    Activations Density 0.009%

    No Known Activations