© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9785
    Prev
    Next
    INDEX
    Explanations

    identity theft/fusion/crisis

    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
    iness
    -0.12
    èĩ¾
    -0.10
    stay
    -0.10
    ness
    -0.10
    ishly
    -0.09
    bery
    -0.09
    ÑĪие
    -0.09
    ifier
    -0.09
    istan
    -0.09
    anke
    -0.09
    POSITIVE LOGITS
    å¢ħ
    0.10
    åįģ足
    0.10
    rame
    0.10
    rama
    0.09
    符
    0.09
     Theft
    0.09
    åīIJ
    0.09
    ê°IJ
    0.09
    riz
    0.09
    arro
    0.09
    Activations Density 0.014%

    No Known Activations