© 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. 22213
    Prev
    Next
    INDEX
    Explanations

    poly technical institute

    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
    aber
    -0.11
    oint
    -0.10
    apes
    -0.10
    yard
    -0.09
    æĪijå½ĵæŶ
    -0.09
    angler
    -0.09
    oints
    -0.09
    /loader
    -0.09
    à¹ĥ
    -0.08
    беÑĢ
    -0.08
    POSITIVE LOGITS
    itive
    0.12
    (Program
    0.11
    jabi
    0.10
    entially
    0.10
    formance
    0.10
    ultimate
    0.10
    åĵ®
    0.09
    лав
    0.09
    ably
    0.09
    ynomial
    0.09
    Activations Density 1.596%

    No Known Activations