© 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. 57257
    Prev
    Next
    INDEX
    Explanations

    ing or ous endings

    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
    ëį°
    -0.16
    maal
    -0.11
     ’
    -0.10
    หมà¸Ķ
    -0.10
    azon
    -0.10
    Ùħا
    -0.09
    ÑĤе
    -0.09
    åģĵ
    -0.09
    parable
    -0.09
    orch
    -0.09
    POSITIVE LOGITS
    ing
    0.54
    Ø©
    0.26
    ãĤĭ
    0.24
    ING
    0.23
    a
    0.22
    а
    0.19
    า
    0.18
    ting
    0.18
    entication
    0.17
    ning
    0.16
    Activations Density 2.167%

    No Known Activations