© 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. 35359
    Prev
    Next
    INDEX
    Explanations

    villa

    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
    åħ¶æīĢ
    -0.10
    eds
    -0.10
    å½ĵåľ°äºº
    -0.10
    -0.10
    碲
    -0.09
    æ¡£
    -0.09
    åĨĻçĿĢ
    -0.09
    -legged
    -0.09
    ives
    -0.09
    INC
    -0.09
    POSITIVE LOGITS
    iard
    0.10
    ég
    0.10
    pite
    0.09
    åŃIJéĩĮ
    0.09
    ustr
    0.09
    èĭ£
    0.09
    ï¸
    0.09
    fred
    0.09
    ier
    0.09
    azon
    0.09
    Activations Density 0.014%

    No Known Activations