© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53178
    Prev
    Next
    INDEX
    Explanations

    names ending in da/a/nda

    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
    zelf
    -0.12
    htag
    -0.12
    转载
    -0.09
    istic
    -0.09
    ened
    -0.09
    ä¸ĭæĿ¥
    -0.08
    adecimal
    -0.08
    v
    -0.08
    NAS
    -0.08
    mitter
    -0.08
    POSITIVE LOGITS
    ero
    0.10
    å¹ħ
    0.10
    ãģŁãĤģ
    0.10
    æ¦Ń
    0.10
    çĨĦ
    0.09
    Ä°K
    0.09
    SOR
    0.09
    theon
    0.09
    iare
    0.09
     Rae
    0.09
    Activations Density 0.007%

    No Known Activations