© 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. 3828
    Prev
    Next
    INDEX
    Explanations

    series titles and names

    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
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    door
    -0.08
    åıĹåĪ°äºĨ
    -0.08
    æ±ĤãĤģ
    -0.08
    综åIJĪä½ĵ
    -0.08
     zaj
    -0.08
    langs
    -0.08
    æľ¬èĥ½
    -0.08
    éķ¿ä¹ħ
    -0.08
    æ±ĩéĽĨ
    -0.08
    POSITIVE LOGITS
    RAND
    0.10
    _lb
    0.09
    chos
    0.09
    å¤ĦåĪĨ
    0.09
    åĢĻ
    0.09
    ienes
    0.09
     Wine
    0.08
    èģĺ
    0.08
    ecycle
    0.08
    ÑĤай
    0.08
    Activations Density 0.052%

    No Known Activations