© 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. 37734
    Prev
    Next
    INDEX
    Explanations

    actual implementation or results

    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
    ä¸įæĦ¿
    -0.09
     rej
    -0.09
     hop
    -0.08
    aze
    -0.08
    åIJİåı°
    -0.08
    _idxs
    -0.08
    åĪ«è¯´
    -0.08
    ç¼±
    -0.07
    绾
    -0.07
     kept
    -0.07
    POSITIVE LOGITS
    å®ŀéĻħ
    0.22
     actual
    0.19
    çļĦå®ŀéĻħ
    0.18
    å®ŀéĻħè¡ĮåĬ¨
    0.16
    å®ŁéļĽãģ«
    0.16
    actual
    0.15
    實éļĽ
    0.15
    (actual
    0.15
     Actual
    0.15
    åħ·ä½ĵçļĦ
    0.15
    Activations Density 0.208%

    No Known Activations