© 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. 6334
    Prev
    Next
    INDEX
    Explanations

    citrus fruit and Citrix Systems

    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
    ×ķת
    -0.12
    ings
    -0.11
    sWith
    -0.11
    ingo
    -0.10
    agements
    -0.09
    Selectors
    -0.09
    é«®
    -0.09
    PRESENT
    -0.09
    ingham
    -0.09
    aho
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    ophil
    0.10
    nier
    0.10
    åŃIJå¼Ł
    0.09
    on
    0.09
    ä¸ĢæĬ¹
    0.09
    çŁ¥éģĵèĩªå·±
    0.09
    itious
    0.08
    ised
    0.08
    æĬ¹
    0.08
    Activations Density 0.010%

    No Known Activations