© 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. 49098
    Prev
    Next
    INDEX
    Explanations

    of god

    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
    itty
    -0.09
    ãģıãĤĭ
    -0.09
    amar
    -0.09
    oler
    -0.09
    åĽ½åĨħå¤ĸ
    -0.09
    amera
    -0.08
    åĽĽå¤Ħ
    -0.08
    asha
    -0.08
    iband
    -0.08
    sonian
    -0.08
    POSITIVE LOGITS
    mium
    0.10
    人群ä¸Ń
    0.09
    thon
    0.09
    å¿ĥæĦ¿
    0.09
    oit
    0.09
    çĤ¹éĴŁ
    0.09
     اÙĦتابعة
    0.09
    gether
    0.08
    游æĪıéĩĮçļĦ
    0.08
    layan
    0.08
    Activations Density 0.079%

    No Known Activations