© 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. 32412
    Prev
    Next
    INDEX
    Explanations

    applications and contexts

    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
    4
    -0.10
    5
    -0.10
    6
    -0.10
    8
    -0.09
     stump
    -0.09
    7
    -0.09
    åĪ®
    -0.09
    0
    -0.09
    3
    -0.08
    9
    -0.08
    POSITIVE LOGITS
     applications
    0.14
    _application
    0.13
     пÑĢименениÑı
    0.13
     Applications
    0.12
     application
    0.12
    applications
    0.12
    åºĶçĶ¨
    0.12
    (application
    0.12
    é¢ĨåŁŁ
    0.11
    Applications
    0.11
    Activations Density 0.171%

    No Known Activations