© 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. 63235
    Prev
    Next
    INDEX
    Explanations

    mountains

    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
    æµ·åºķ
    -0.09
    leur
    -0.09
    æĺŁçIJĥ
    -0.08
    åı¸
    -0.08
    kie
    -0.08
    äºĮ线
    -0.08
    鹫
    -0.08
    åĵ¡å·¥
    -0.08
    äºĶåĪĨéĴŁ
    -0.08
    èĭ«
    -0.08
    POSITIVE LOGITS
    غÙĪ
    0.08
    arov
    0.08
    éĿ©
    0.08
    wide
    0.07
    andr
    0.07
    èĦļ
    0.07
    æºħ
    0.07
    phans
    0.07
    èħ³
    0.07
     Baylor
    0.07
    Activations Density 0.017%

    No Known Activations