© 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. 62905
    Prev
    Next
    INDEX
    Explanations

    for its/their

    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
    è¿ľ
    -0.08
    说æ³ķ
    -0.08
    erg
    -0.08
    .offsetTop
    -0.08
    åĸĦæĦı
    -0.08
     Busy
    -0.08
    æľīåĬĽ
    -0.07
     новоÑģÑĤи
    -0.07
    渡
    -0.07
    -guard
    -0.07
    POSITIVE LOGITS
    å®ĥçļĦ
    0.18
    åĽłä¸ºå®ĥ
    0.18
    åħ¶
    0.16
     its
    0.15
    åĽłåħ¶
    0.14
     Its
    0.13
    Its
    0.12
    çīł
    0.12
    åħ¶æīĢ
    0.12
    å®ĥ
    0.11
    Activations Density 0.122%

    No Known Activations