© 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. 57202
    Prev
    Next
    INDEX
    Explanations

    amic, ami, amicably, amigo, amitriptyline

    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
    former
    -0.09
    que
    -0.09
    помн
    -0.09
    arding
    -0.08
    ning
    -0.08
    æŃ£å½ĵ
    -0.08
    æĥ³çŁ¥éģĵ
    -0.08
    cast
    -0.08
    OrUpdate
    -0.08
    ÑģÑĤавлен
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    ioned
    0.09
     Baths
    0.09
    纶
    0.09
    riad
    0.09
    æijĩ
    0.09
    innen
    0.09
     à¹Ĩ
    0.08
    èIJ©
    0.08
    æĢ§å¼º
    0.08
    Activations Density 0.025%

    No Known Activations