© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    version of X

    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
    èł¡
    -0.09
    ACT
    -0.08
    udu
    -0.08
    åľ©
    -0.08
     Kah
    -0.08
    å¦Ĵ
    -0.08
    peech
    -0.08
    åį´è¢«
    -0.08
    å®ĵ
    -0.08
    æ»ģ
    -0.08
    POSITIVE LOGITS
    /pm
    0.10
    imat
    0.10
    trl
    0.10
    温馨
    0.09
    inka
    0.09
    IMER
    0.09
    éĥ½æľīçĿĢ
    0.09
    蹩
    0.08
    åĪĽæĸ°åıijå±ķ
    0.08
    _TERMIN
    0.08
    Activations Density 0.023%

    No Known Activations