© 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. 58171
    Prev
    Next
    INDEX
    Explanations

    Cheryl and related 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
    uchar
    -0.10
    趸
    -0.10
    ×ķת
    -0.09
    æł·çļĦ
    -0.09
    ehler
    -0.09
    uga
    -0.09
    enheim
    -0.09
    oter
    -0.08
    ober
    -0.08
    AndView
    -0.08
    POSITIVE LOGITS
    ners
    0.10
    son
    0.10
    ship
    0.09
    smith
    0.09
    tha
    0.09
    aceous
    0.09
    ning
    0.09
     поиÑģк
    0.09
    ssid
    0.08
    ns
    0.08
    Activations Density 0.011%

    No Known Activations