© 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. 5150
    Prev
    Next
    INDEX
    Explanations

    by appointment or on request

    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
    褥
    -0.09
    åºĬä¸Ĭ
    -0.09
    .stderr
    -0.08
    æīĵæŃ»
    -0.08
    æīĵ好
    -0.08
    -inline
    -0.08
    /end
    -0.08
    åIJ½
    -0.08
    纵横
    -0.08
    ỡ
    -0.08
    POSITIVE LOGITS
    èĥģ
    0.08
    åı¬
    0.08
    lip
    0.08
     specifications
    0.08
    çĹī
    0.08
    ocy
    0.08
    æ¡ĥèĬ±
    0.08
     kir
    0.08
    ams
    0.08
    lad
    0.08
    Activations Density 0.090%

    No Known Activations