© 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. 48330
    Prev
    Next
    INDEX
    Explanations

    physical openings and access points

    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
     Pru
    -0.09
    AML
    -0.09
    æĢª
    -0.09
    Lng
    -0.09
    çŀŁ
    -0.08
    OCI
    -0.08
    è¹²
    -0.08
    erce
    -0.08
    æľīåĬ©
    -0.08
    ewan
    -0.08
    POSITIVE LOGITS
    åħ¥åı£
    0.13
     entrance
    0.12
    å¤Ħ
    0.11
    è¿Ľåħ¥
    0.11
     entrances
    0.09
    è¸ıåħ¥
    0.09
    大éŨ
    0.09
    åħ¥åľº
    0.09
     entrada
    0.09
    éĢ²åħ¥
    0.09
    Activations Density 0.043%

    No Known Activations