© 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. 18709
    Prev
    Next
    INDEX
    Explanations

    SIM card and phone messages

    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
    çļĤ
    -0.09
    æĦŁè§ī
    -0.09
    羣å®ŀçļĦ
    -0.09
    rab
    -0.09
    èŀįåªĴä½ĵ
    -0.08
    åħ¬æĬ¥
    -0.08
    itzer
    -0.08
    nik
    -0.08
    iore
    -0.08
    æķĪçİĩ
    -0.08
    POSITIVE LOGITS
    imei
    0.10
    ç«£
    0.09
    æ¡£
    0.09
    otr
    0.08
    æīĭæľºåı·
    0.08
    亲åıĭ
    0.08
     eject
    0.08
    /trunk
    0.08
    æĪIJåĵģ
    0.08
    汶
    0.08
    Activations Density 0.119%

    No Known Activations