© 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. 62964
    Prev
    Next
    INDEX
    Explanations

    we followed by verbs

    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
    tes
    -0.11
    ä¼ļå¼ķèµ·
    -0.10
    sWith
    -0.10
    sc
    -0.10
    ially
    -0.10
    ity
    -0.10
    ses
    -0.09
    son
    -0.09
    åŃIJéĩĮ
    -0.09
    -minded
    -0.09
    POSITIVE LOGITS
    brtc
    0.13
    ä¿©
    0.13
    akest
    0.13
    andering
    0.12
    çļĦ人çĶŁ
    0.12
    bservice
    0.12
    çļĦä¸ĢåĪĩ
    0.11
    athers
    0.11
    olding
    0.11
    -même
    0.11
    Activations Density 0.200%

    No Known Activations