© 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. 33673
    Prev
    Next
    INDEX
    Explanations

    emphasis

    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
    亲çĪ±
    -0.09
    容
    -0.08
    æ¨
    -0.08
    泸
    -0.08
    ä¸Ģè¶Ł
    -0.08
    avel
    -0.08
    ARB
    -0.07
    -minded
    -0.07
    fen
    -0.07
     minded
    -0.07
    POSITIVE LOGITS
    强è°ĥ
    0.11
    åĭĥåĭĥ
    0.11
    rush
    0.11
    ÑĢаÑģÑĤ
    0.11
     emphasis
    0.11
    placed
    0.10
    åĪĨæĺİ
    0.10
    å¸Ī
    0.10
    çªģåĩº
    0.10
    Intensity
    0.09
    Activations Density 0.017%

    No Known Activations