© 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. 11573
    Prev
    Next
    INDEX
    Explanations

    css stylesheet files

    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
    èħ¹
    -0.09
    æIJŃ
    -0.09
    MouseButton
    -0.09
    reb
    -0.09
    ç¬ij
    -0.09
    éĽģ
    -0.08
    åѵåĮĸåĻ¨
    -0.08
    çĩ§
    -0.08
    çijľ
    -0.08
    BERS
    -0.08
    POSITIVE LOGITS
    åıijæī¬
    0.12
     stylesheet
    0.11
    (css
    0.11
    stylesheet
    0.11
    (styles
    0.10
    .css
    0.10
     styles
    0.10
    .CSS
    0.10
    StyleSheet
    0.10
     CSS
    0.10
    Activations Density 0.494%

    No Known Activations