© 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. 31541
    Prev
    Next
    INDEX
    Explanations

    charities and nonprofits

    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©´
    -0.10
    åī¥
    -0.10
    çīĩ
    -0.09
    arius
    -0.09
    roz
    -0.09
     Overse
    -0.08
    æĬµåĪ¶
    -0.08
     Zus
    -0.08
    æİīèIJ½
    -0.08
    /display
    -0.08
    POSITIVE LOGITS
    enthal
    0.10
    åĪĽä¸ļèĢħ
    0.09
    vit
    0.09
    onald
    0.09
    åµ´
    0.09
    ç¦ĺ
    0.09
    _sector
    0.08
    好æľĭåıĭ
    0.08
    обоÑĢ
    0.08
    unge
    0.08
    Activations Density 0.017%

    No Known Activations