© 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. 28127
    Prev
    Next
    INDEX
    Explanations

    review coverage

    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
    èį¥
    -0.09
    身价
    -0.09
    _ZONE
    -0.09
    BBC
    -0.09
    Equip
    -0.08
    wyn
    -0.08
     Mage
    -0.08
    èĻİ
    -0.08
    OSE
    -0.08
    .SelectedValue
    -0.08
    POSITIVE LOGITS
    è¯Ħ
    0.10
    çĤ¹è¯Ħ
    0.10
    è¯Ħä»·
    0.09
    èį¡
    0.09
    è··
    0.09
    mdb
    0.09
    ubre
    0.09
    ulum
    0.09
    åįģåŃĹ
    0.08
    åijķ
    0.08
    Activations Density 0.038%

    No Known Activations