© 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. 3694
    Prev
    Next
    INDEX
    Explanations

    legal and medical degrees

    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
    æ°Ķæ°Ľ
    -0.10
    uel
    -0.09
    etter
    -0.08
    lish
    -0.08
    _specs
    -0.08
    åĽ¢åijĺ
    -0.08
    ocl
    -0.08
    ainer
    -0.08
    oningen
    -0.08
    uhn
    -0.08
    POSITIVE LOGITS
    åĿ³
    0.10
    çĴIJ
    0.09
    éĻĤ
    0.09
    çĥ¤
    0.09
    çĪ±ç¾İ
    0.08
    è¾ķ
    0.08
    2
    0.08
    åŁ´
    0.08
    arts
    0.08
    IRS
    0.08
    Activations Density 0.011%

    No Known Activations