© 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. 27497
    Prev
    Next
    INDEX
    Explanations

    nuts and nut butters

    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
    ature
    -0.10
    nze
    -0.09
    heets
    -0.09
    ophile
    -0.09
    usz
    -0.09
    yon
    -0.09
    ilarity
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    åıijåŀĭ
    -0.08
    ponent
    -0.08
    POSITIVE LOGITS
    迨
    0.09
    ritional
    0.09
    meg
    0.09
    åIJİèĢħ
    0.09
    weg
    0.08
    sv
    0.08
    ony
    0.08
    воÑĢ
    0.08
    usercontent
    0.08
    溪
    0.08
    Activations Density 0.015%

    No Known Activations