© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    stone or milestone compounds

    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
    ĵ
    -0.11
    rence
    -0.10
    ison
    -0.10
    ness
    -0.10
    acity
    -0.10
    sons
    -0.10
    inition
    -0.09
    otr
    -0.09
    nder
    -0.09
    lock
    -0.09
    POSITIVE LOGITS
    arity
    0.10
    æѤåĪ»
    0.10
    papers
    0.10
    çİ«
    0.10
     marrow
    0.09
    ledge
    0.09
    æĻ°
    0.09
    egg
    0.09
    bjerg
    0.09
    otle
    0.09
    Activations Density 0.026%

    No Known Activations