© 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. 57102
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    PCS
    -0.13
    ç²¹
    -0.10
     Sized
    -0.09
    íĮ¨
    -0.09
    ivate
    -0.09
    èĭij
    -0.09
    ç¥Ł
    -0.09
    çĸij
    -0.08
     Caught
    -0.08
    rant
    -0.08
    POSITIVE LOGITS
    oretical
    0.08
    _DGRAM
    0.08
    cestor
    0.08
    .hm
    0.08
    说起
    0.07
    ä¸įè´Ł
    0.07
     Stam
    0.07
    ailles
    0.07
    esimal
    0.07
    iform
    0.07
    Activations Density 0.649%

    No Known Activations