© 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. 3746
    Prev
    Next
    INDEX
    Explanations

    Ali, Ali's, alias, Ali-related names

    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
    sWith
    -0.13
    eenth
    -0.10
    lop
    -0.09
    ially
    -0.09
    acho
    -0.09
    -thirds
    -0.09
    å¤§éĽ¨
    -0.09
    éĵ«
    -0.08
    ulos
    -0.08
     slu
    -0.08
    POSITIVE LOGITS
    ระ
    0.10
    (alias
    0.09
    andro
    0.09
    0.09
     ske
    0.09
     dụng
    0.09
    iances
    0.09
     ali
    0.09
    raries
    0.09
    coln
    0.09
    Activations Density 0.022%

    No Known Activations