© 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. 32562
    Prev
    Next
    INDEX
    Explanations

    common phrases and phrases following them

    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
    иÑģ
    -0.08
    ISK
    -0.08
    ãģ¨ãģ®ãģĵãģ¨
    -0.08
    éļį
    -0.08
     ìĿ¼
    -0.08
    è°ħ
    -0.08
    çĿļ
    -0.08
    nym
    -0.07
    Ế
    -0.07
    ebra
    -0.07
    POSITIVE LOGITS
    å¹²èĦĨ
    0.08
    ayar
    0.08
    errs
    0.08
    æĺİçıł
    0.08
     Accom
    0.07
    å°ģ
    0.07
    éĿ©
    0.07
     anyway
    0.07
    irit
    0.07
    -*-
    0.07
    Activations Density 0.150%

    No Known Activations