© 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. 49501
    Prev
    Next
    INDEX
    Explanations

    marijuana legalization and medical use

    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
    æĢ¥
    -0.10
    æ¸Ķ
    -0.10
    rms
    -0.08
    å¾ĹæĦı
    -0.08
    åĩºæīĭ
    -0.08
    uter
    -0.08
    æĢĤ
    -0.08
    itzer
    -0.08
    讣
    -0.08
    prot
    -0.08
    POSITIVE LOGITS
    å§ij
    0.11
    ä¸İåIJ¦
    0.10
    æĮĩçĤ¹
    0.09
    CharCode
    0.09
    湿润
    0.09
    argout
    0.09
    addir
    0.09
    .addObject
    0.09
    adge
    0.08
    igue
    0.08
    Activations Density 0.030%

    No Known Activations