© 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. 27625
    Prev
    Next
    INDEX
    Explanations

    Wired, Wi-Fi, Mobile, GPL

    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
    åĮĸè¿Ľç¨ĭ
    -0.09
    çī¹åĪ«æĺ¯
    -0.08
    åħij
    -0.08
    大åݦ
    -0.08
    è±ģ
    -0.08
    åı«åģļ
    -0.08
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    _EXPR
    -0.07
    åĴ¿
    -0.07
    èĢĨ
    -0.07
    POSITIVE LOGITS
    å´Ń
    0.10
    çģ°èī²
    0.09
    å®Įç¾İ
    0.09
    以åħ¶
    0.09
    示èĮĥåĮº
    0.09
    åĬłç´§
    0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
    ä¸įäºĨ
    0.08
    &amp
    0.08
    avra
    0.08
    Activations Density 0.245%

    No Known Activations