© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    deferral or inference

    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
    ย
    -0.10
    yan
    -0.09
    gg
    -0.09
     slate
    -0.08
    овоÑĢ
    -0.08
    tw
    -0.08
    /her
    -0.08
    é«®
    -0.08
    ±
    -0.08
    -hearted
    -0.08
    POSITIVE LOGITS
    rence
    0.10
    ance
    0.10
    esto
    0.10
    ighted
    0.10
    æ·ĭ
    0.09
    entially
    0.09
    usal
    0.09
    centage
    0.09
    bie
    0.09
    çľ¼ä¸ĭ
    0.09
    Activations Density 0.010%

    No Known Activations