© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by words

    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
    ewe
    -0.10
    esto
    -0.09
    ãĢħ
    -0.09
    ãģĦãģ¦
    -0.09
    IDI
    -0.09
    çİ«
    -0.09
    ently
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    OrNull
    -0.08
    vida
    -0.08
    POSITIVE LOGITS
    zelf
    0.12
    s
    0.11
    ãĢģãĢĮ
    0.11
    a
    0.10
    åľ¨å¤ĸéĿ¢
    0.10
    ãĥ³
    0.10
    ftware
    0.10
    and
    0.10
    ãĤĪãģĨãģª
    0.10
    缸åħ³åĨħ容
    0.10
    Activations Density 1.026%

    No Known Activations