© 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. 48953
    Prev
    Next
    INDEX
    Explanations

    to new

    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
    éŀŃ
    -0.10
    éħ¿
    -0.09
    USE
    -0.09
    èĪĽ
    -0.09
    erna
    -0.09
    esian
    -0.09
    lland
    -0.09
    isto
    -0.08
    ucher
    -0.08
    èľ¡
    -0.08
    POSITIVE LOGITS
    大è¡Ĺ
    0.11
    åĸ½
    0.09
    è°Ĵ
    0.08
    à¹Ħหà¸Ļ
    0.08
    inda
    0.08
    竺
    0.08
    绣绣
    0.08
    é¦ĸä½į
    0.08
    ç»ĪçĤ¹
    0.08
    obar
    0.07
    Activations Density 0.022%

    No Known Activations