© 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. 23475
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    ç©¿è¡£
    -0.10
    èĢģ人家
    -0.10
    å¤§åľ°
    -0.09
    ä»»ä½ķ人
    -0.09
    ooth
    -0.09
    eres
    -0.09
    ovsky
    -0.09
     AppComponent
    -0.09
    porn
    -0.09
    verty
    -0.09
    POSITIVE LOGITS
    æīĢåģļçļĦ
    0.09
    媳
    0.09
    hood
    0.08
    UNC
    0.08
    ory
    0.08
    å®°
    0.08
    ds
    0.08
    ена
    0.08
    mentation
    0.08
    len
    0.08
    Activations Density 0.006%

    No Known Activations