© 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. 62910
    Prev
    Next
    INDEX
    Explanations

    license subject

    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
    åĪĺéĤ¦
    -0.09
    nett
    -0.08
     (*((
    -0.08
    ượng
    -0.08
    请大家
    -0.08
     JIT
    -0.08
    зал
    -0.08
    .reserve
    -0.08
    é«ĵ
    -0.08
    å¹´å¤ľ
    -0.08
    POSITIVE LOGITS
    èģļåIJĪ
    0.10
    anter
    0.09
    ola
    0.09
    ivet
    0.09
    å¹´è½»çļĦ
    0.08
    çĤľ
    0.08
    微信群
    0.08
    velt
    0.08
    _AUX
    0.08
    çĤ¸
    0.08
    Activations Density 0.014%

    No Known Activations