© 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. 48531
    Prev
    Next
    INDEX
    Explanations

    ha followed by certain words

    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
    urt
    -0.10
    amina
    -0.10
    ally
    -0.10
    ãĤīãģļ
    -0.10
    urator
    -0.10
    éĻIJ度
    -0.09
    ×Ļ×ķ
    -0.09
    åijĺ
    -0.09
    ERIC
    -0.09
    å²Ĺ
    -0.09
    POSITIVE LOGITS
    htag
    0.10
    ä¸ĢåĪ»
    0.09
    ettel
    0.09
    ideo
    0.09
     sido
    0.09
     ÑĥÑģи
    0.08
    eres
    0.08
    htags
    0.08
    riott
    0.08
    axter
    0.08
    Activations Density 0.021%

    No Known Activations