© 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. 57128
    Prev
    Next
    INDEX
    Explanations

    treatments and conditions

    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
    姿åĬ¿
    -0.09
    çĤĬ
    -0.09
    é«ĺ级
    -0.08
    liv
    -0.08
    大å®Ĺ
    -0.08
    åį¿
    -0.08
     liv
    -0.08
     Lair
    -0.08
    é«ĺåİĭ
    -0.08
    icom
    -0.08
    POSITIVE LOGITS
    ertools
    0.12
    é²ģ
    0.10
    æĹ¶ä»£
    0.09
    enso
    0.09
    bens
    0.09
     Uncle
    0.09
    åŬ
    0.09
    麻
    0.09
    eln
    0.08
    itur
    0.08
    Activations Density 0.008%

    No Known Activations