© 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. 27367
    Prev
    Next
    INDEX
    Explanations

    traffic lights

    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
    hand
    -0.09
    fare
    -0.09
     Cups
    -0.09
    apat
    -0.09
    iston
    -0.08
    ptive
    -0.08
    duit
    -0.08
    èĥĮéĥ¨
    -0.08
    oleon
    -0.08
    isci
    -0.08
    POSITIVE LOGITS
    çĽı
    0.10
    èĦ
    0.09
    æĺı
    0.09
    bul
    0.09
    åŁºè¾ħ
    0.09
    tro
    0.09
    åĴĮ个人
    0.09
    reich
    0.08
    åĿıäºĨ
    0.08
    artment
    0.08
    Activations Density 0.011%

    No Known Activations