© 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. 54733
    Prev
    Next
    INDEX
    Explanations

    handling and its consequences

    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
     далек
    -0.09
    oure
    -0.08
    reb
    -0.08
    é¢Ĩ
    -0.08
    eker
    -0.08
    acts
    -0.08
    orro
    -0.08
    dain
    -0.08
    andas
    -0.08
     INC
    -0.08
    POSITIVE LOGITS
    adores
    0.10
    çĻĸ
    0.09
    åĪĽéĢłåĩº
    0.09
    éĢĬ
    0.09
    LM
    0.09
    ä¸ĬçļĦ
    0.09
     Briggs
    0.09
    èIJ¥åķĨ
    0.09
    è¯ģçĽij
    0.08
    ëŀŃ
    0.08
    Activations Density 0.014%

    No Known Activations