© 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. 28034
    Prev
    Next
    INDEX
    Explanations

    Francis J. and subsequent names

    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
    ings
    -0.10
    avax
    -0.10
     lÆ°ng
    -0.10
    ingly
    -0.10
    姥
    -0.09
    æĹİ
    -0.09
    edReader
    -0.09
    è¯Ł
    -0.09
    å®ĺåı¸
    -0.09
    ãĤĮ
    -0.09
    POSITIVE LOGITS
     Xavier
    0.11
    zek
    0.09
    Ñħод
    0.09
    uation
    0.09
    ythe
    0.09
    ëĬĶëį°
    0.09
    fully
    0.09
    itious
    0.08
     thơ
    0.08
    eur
    0.08
    Activations Density 0.028%

    No Known Activations