© 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. 37948
    Prev
    Next
    INDEX
    Explanations

    belonging to

    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
    -eyed
    -0.10
    usal
    -0.09
    ngle
    -0.09
    ifiable
    -0.09
    lake
    -0.09
    burgh
    -0.08
    nger
    -0.08
    éĢĬ
    -0.08
    Invoker
    -0.08
     диз
    -0.08
    POSITIVE LOGITS
    ancy
    0.12
    AnimationFrame
    0.10
    sworth
    0.09
    åľ¨ä¸Ĭæµ·
    0.09
    纩
    0.09
    åľ¨ç¾İåĽ½
    0.08
    ÑģÑĤве
    0.08
    ance
    0.08
    ocal
    0.08
    chaft
    0.08
    Activations Density 0.022%

    No Known Activations