© 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. 21732
    Prev
    Next
    INDEX
    Explanations

    essay and context

    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
    åŃĹåı·
    -0.10
    ovel
    -0.09
    dddd
    -0.09
    ëģĶ
    -0.09
    nit
    -0.08
    outs
    -0.08
     quo
    -0.08
    pa
    -0.08
     Fé
    -0.08
    ché
    -0.08
    POSITIVE LOGITS
    ields
    0.10
    çĩ®
    0.10
    rium
    0.10
    itis
    0.10
    .jupiter
    0.09
     طرÙĬÙĤ
    0.09
    otron
    0.09
    agger
    0.09
    仪
    0.09
    egrator
    0.09
    Activations Density 0.018%

    No Known Activations