© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    un- prefix

    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
    reen
    -0.09
    emia
    -0.08
    ief
    -0.08
    åIJĪæ³ķ
    -0.08
    Optimizer
    -0.08
    obook
    -0.08
    upe
    -0.08
    od
    -0.08
    iane
    -0.08
    çľĭçĹħ
    -0.08
    POSITIVE LOGITS
    æŃ¤äºº
    0.10
    移åĪ°
    0.09
    bles
    0.09
    士
    0.09
    æĹłå£°
    0.09
    erson
    0.09
    ASY
    0.08
    ments
    0.08
    _VALIDATE
    0.08
    æĹłå½¢
    0.08
    Activations Density 0.016%

    No Known Activations