© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    reopened, again, back

    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
    æ¤ħ
    -0.09
    vana
    -0.08
     Zuk
    -0.08
    ä»į
    -0.08
    thest
    -0.08
    çŀĢ
    -0.08
    .quick
    -0.08
    èĬĴ
    -0.08
    flower
    -0.08
    /Area
    -0.08
    POSITIVE LOGITS
    inson
    0.10
    æĬ¼
    0.09
    æľ¬åĽ½
    0.09
    çĿ½
    0.09
    infeld
    0.08
    èIJĨ
    0.08
    åĴĮåıijå±ķ
    0.08
    åı¸
    0.08
    æī©å¼ł
    0.08
    æĬŁ
    0.08
    Activations Density 0.138%

    No Known Activations