© 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. 63830
    Prev
    Next
    INDEX
    Explanations

    fun facts and related words

    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
    çĤİ
    -0.09
    enen
    -0.09
    å¿ĥå¢ĥ
    -0.09
    een
    -0.09
    åĬĽæ±Ĥ
    -0.09
    åŀł
    -0.09
    ains
    -0.09
    azes
    -0.08
    aurus
    -0.08
    ine
    -0.08
    POSITIVE LOGITS
    niest
    0.15
    erals
    0.15
    nels
    0.14
    amental
    0.12
    eral
    0.12
    employed
    0.11
    amentals
    0.11
    ereal
    0.11
    à¸į
    0.11
    ERAL
    0.11
    Activations Density 0.025%

    No Known Activations