© 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. 17532
    Prev
    Next
    INDEX
    Explanations

    person obtaining

    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
    å¾Īå¤ļ人
    -0.11
    led
    -0.10
    篷
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    uer
    -0.09
    ema
    -0.09
    ires
    -0.09
    anter
    -0.09
    ä»»ä½ķ人
    -0.09
     дело
    -0.09
    POSITIVE LOGITS
    nels
    0.18
    nel
    0.17
    NEL
    0.13
    ality
    0.12
    nal
    0.12
    nelle
    0.12
    ually
    0.11
    ajes
    0.11
    nic
    0.11
    ification
    0.10
    Activations Density 0.028%

    No Known Activations