© 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. 61780
    Prev
    Next
    INDEX
    Explanations

    fantastical, fantasy, fantastic

    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
    ÙĤت
    -0.10
    atten
    -0.10
    å¯ĴåĨ¬
    -0.09
    leys
    -0.09
    baugh
    -0.09
    etz
    -0.09
    seau
    -0.09
    heimer
    -0.09
    ãģ£ãģ±
    -0.08
    Ñģ
    -0.08
    POSITIVE LOGITS
    istic
    0.12
    kube
    0.11
    ream
    0.10
    istically
    0.10
    igue
    0.10
    atics
    0.10
    à¸ģาย
    0.09
    ISTIC
    0.09
    rike
    0.09
    ãģıãĤĮ
    0.09
    Activations Density 0.008%

    No Known Activations