© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    workflow

    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
    igr
    -0.10
    ored
    -0.09
    beth
    -0.09
    æİĴè¡Įæ¦ľ
    -0.09
    peed
    -0.08
    à¸ķาร
    -0.08
    аÑĨи
    -0.08
    ains
    -0.08
    ision
    -0.08
    å¿ĥåºķ
    -0.08
    POSITIVE LOGITS
    æµģç¨ĭ
    0.12
    åĨįéĢł
    0.11
    顺çķħ
    0.09
     mates
    0.09
    cept
    0.09
    flows
    0.09
    [color
    0.09
    IPP
    0.09
    ä¼Ļä¼´
    0.09
    Owner
    0.08
    Activations Density 0.033%

    No Known Activations