© 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. 55177
    Prev
    Next
    INDEX
    Explanations

    moist / damp

    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
    naire
    -0.09
    -grade
    -0.09
    zeit
    -0.09
    oretical
    -0.09
    ãĤ
    -0.09
    RED
    -0.08
    bing
    -0.08
    dish
    -0.08
    çİł
    -0.08
    pared
    -0.08
    POSITIVE LOGITS
    ening
    0.16
    ened
    0.15
    æ°²
    0.11
    enido
    0.11
    eur
    0.10
    è¾Ķ
    0.10
    aling
    0.10
    erton
    0.10
    ãģ»ãģĨãģĮ
    0.09
    ments
    0.09
    Activations Density 0.005%

    No Known Activations