© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52782
    Prev
    Next
    INDEX
    Explanations

    labels and values:

    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
    orem
    -0.19
    ä¹İ
    -0.11
    æĢĴ
    -0.09
    ä¸ĥæĺŁ
    -0.09
    è¦ģæĺ¯
    -0.09
    åĨħåľ°
    -0.09
    raries
    -0.09
    ogh
    -0.08
    åĻ«
    -0.08
    æĨ©
    -0.08
    POSITIVE LOGITS
    yclerView
    0.13
    rastructure
    0.12
    èµ·æĿ¥äºĨ
    0.10
    DataGridViewTextBoxColumn
    0.10
    oenix
    0.09
    :///
    0.09
    dın
    0.09
    bidden
    0.09
    claimer
    0.09
    .DEFINE
    0.09
    Activations Density 0.914%

    No Known Activations