© 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. 30104
    Prev
    Next
    INDEX
    Explanations

    the following `Checkout`

    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
    åħľ
    -0.11
    çŃĸåĪĴ
    -0.10
    ä¸įåħĭ
    -0.09
    наÑĤ
    -0.09
    ä¸įæŃ»
    -0.09
    åijĵ
    -0.08
    Paren
    -0.08
    çĦ°
    -0.08
    åı°
    -0.08
    æĭĻ
    -0.08
    POSITIVE LOGITS
    çļĦå¿ĥçIJĨ
    0.10
    ormal
    0.10
    çľĭçĶµå½±
    0.09
    æĻĴ
    0.09
    .Generated
    0.09
    群ä½ĵ
    0.09
    conf
    0.09
    éĿ¢åŃIJ
    0.09
    宥
    0.09
    rox
    0.09
    Activations Density 0.061%

    No Known Activations