© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 870
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    ss
    -0.16
    swith
    -0.15
    sss
    -0.13
    's
    -0.12
    ally
    -0.12
    åĢij
    -0.12
    ssc
    -0.11
    ts
    -0.11
    ter
    -0.11
    aceous
    -0.11
    POSITIVE LOGITS
    sing
    0.18
    s
    0.14
    spe
    0.13
    -speaking
    0.13
    sar
    0.12
    earch
    0.12
    sampling
    0.11
    наÑĩ
    0.11
    sheets
    0.11
    pective
    0.11
    Activations Density 0.061%

    No Known Activations