© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    names/titles before 'M', 'Z', 'Brah', 'J', 'mo'

    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
    ÑģÑĤавил
    -0.09
    spa
    -0.09
    éĻ·
    -0.09
    oble
    -0.08
    alty
    -0.08
     Nicol
    -0.08
    è´©
    -0.08
    çŃīåĨħ容
    -0.08
     pew
    -0.08
    å¼¼
    -0.08
    POSITIVE LOGITS
    è¿ĩæĿ¥
    0.12
    æľį
    0.11
    æ±Ľ
    0.10
    姿
    0.09
    /editor
    0.09
    imity
    0.09
    /lists
    0.09
    åĬ©çIJĨ
    0.09
    érie
    0.09
    .exclude
    0.09
    Activations Density 0.261%

    No Known Activations