© 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. 49097
    Prev
    Next
    INDEX
    Explanations

    res judicata or reserving

    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
    Ñīи
    -0.11
    pping
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    sworth
    -0.10
    ish
    -0.09
    otle
    -0.09
    <dyn
    -0.09
    STER
    -0.09
    à¹Į
    -0.09
    ester
    -0.09
    POSITIVE LOGITS
    ponce
    0.13
    istance
    0.12
    é¹ĥ
    0.11
    idue
    0.11
    çĶ«
    0.10
    ervoir
    0.10
    idency
    0.10
    nce
    0.10
    ervations
    0.10
    ponder
    0.09
    Activations Density 0.062%

    No Known Activations