© 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. 22823
    Prev
    Next
    INDEX
    Explanations

    Nexus, Pixel, or device names, followed by specific terms

    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
    sWith
    -0.10
    оÑı
    -0.09
    sel
    -0.09
    ened
    -0.09
    ening
    -0.09
    iture
    -0.09
    侯
    -0.08
    etro
    -0.08
    down
    -0.08
    abilit
    -0.08
    POSITIVE LOGITS
    icut
    0.10
    æģIJ
    0.10
    çݺ
    0.09
    çĹĽ
    0.09
    ãģĦãģı
    0.09
    TabIndex
    0.09
    ial
    0.09
    hell
    0.09
    iali
    0.09
    æľºåŀĭ
    0.09
    Activations Density 0.005%

    No Known Activations