© 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. 39239
    Prev
    Next
    INDEX
    Explanations

    inf, irc, ath prefixes

    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
    ../../../
    -0.12
    -0.11
    otle
    -0.11
    oft
    -0.10
    keit
    -0.10
    ä½Ĩè¿Ļ
    -0.10
    upo
    -0.10
    terior
    -0.09
    orts
    -0.09
    ĭ
    -0.09
    POSITIVE LOGITS
    usive
    0.12
    ness
    0.12
    ened
    0.11
    els
    0.10
    oring
    0.10
    ening
    0.10
    ention
    0.09
    بار
    0.09
    оÑĢ
    0.09
    lore
    0.09
    Activations Density 0.254%

    No Known Activations