© 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. 33290
    Prev
    Next
    INDEX
    Explanations

    views of mountains and city

    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
    çĪ±ç¾İ
    -0.10
    åĻ©
    -0.10
    éĻ¤
    -0.09
    磾
    -0.09
    ç¾Ķ
    -0.09
    å´İ
    -0.08
    ä¼Ľ
    -0.08
    èµ°è·¯
    -0.08
    æĬµ
    -0.08
    owski
    -0.08
    POSITIVE LOGITS
    è¿ľå¤Ħ
    0.10
    æĻ¯èī²
    0.09
    _demand
    0.09
    åij¨åĽ´
    0.09
    awy
    0.09
    imize
    0.09
     sor
    0.08
    kit
    0.08
    åij¨åĽ´çļĦ
    0.08
    cheid
    0.08
    Activations Density 0.184%

    No Known Activations