© 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. 47989
    Prev
    Next
    INDEX
    Explanations

    stand or standpoint

    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
    arty
    -0.11
    ight
    -0.10
    idge
    -0.10
    zem
    -0.10
    ted
    -0.09
    atron
    -0.09
    ution
    -0.09
    ÑģÑĤанов
    -0.09
     ÑģамоÑģÑĤоÑı
    -0.09
    ën
    -0.08
    POSITIVE LOGITS
    ings
    0.12
    -alone
    0.11
    INGS
    0.10
    ificance
    0.10
    /or
    0.10
    heets
    0.10
    iola
    0.09
    /testify
    0.09
    uario
    0.09
    iful
    0.09
    Activations Density 0.037%

    No Known Activations