© 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. 58644
    Prev
    Next
    INDEX
    Explanations

    paper of

    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
    ively
    -0.10
    eat
    -0.10
    yor
    -0.10
    Ĵ
    -0.09
    yen
    -0.09
    ê°Ŀ
    -0.09
    -Pacific
    -0.09
    sch
    -0.09
    Ìģ
    -0.09
    cy
    -0.08
    POSITIVE LOGITS
    matic
    0.12
    centage
    0.11
    doll
    0.10
    è¾Ī
    0.09
    maid
    0.09
    çıij
    0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    untu
    0.08
    ter
    0.08
    好ä¸į容æĺĵ
    0.08
    Activations Density 0.033%

    No Known Activations