© 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. 10204
    Prev
    Next
    INDEX
    Explanations

    questionnaire

    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
    icine
    -0.10
    ication
    -0.10
    quist
    -0.10
    icated
    -0.10
    loys
    -0.09
    ersh
    -0.09
    acing
    -0.09
    éĤ£åıª
    -0.09
    ä¸ĩ家
    -0.09
    ละ
    -0.08
    POSITIVE LOGITS
    naire
    0.21
    naires
    0.18
    nement
    0.11
    aire
    0.11
    er
    0.10
    stellung
    0.10
    éĩįéĩį
    0.10
    ãģĻãģ§ãģ«
    0.10
    èľĵ
    0.09
     volta
    0.09
    Activations Density 0.069%

    No Known Activations