© 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. 48763
    Prev
    Next
    INDEX
    Explanations

    Ni names

    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
    æīİ
    -0.09
    uster
    -0.09
    ookie
    -0.09
    辫
    -0.09
    ick
    -0.08
    æ±Ĺ
    -0.08
    eny
    -0.08
    ordo
    -0.08
    usting
    -0.08
    enis
    -0.08
    POSITIVE LOGITS
    ernet
    0.10
    icip
    0.09
    поÑĩ
    0.09
    annel
    0.09
    nicos
    0.09
    otic
    0.09
    ç©¿è¡£
    0.08
    ä½ĵ温
    0.08
    gli
    0.08
    icode
    0.08
    Activations Density 0.043%

    No Known Activations