© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19940
    Prev
    Next
    INDEX
    Explanations

    invasive, invasion, invaded

    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
    è¾Ī
    -0.12
    çĿ¬
    -0.11
    sch
    -0.10
    lessly
    -0.10
    ening
    -0.10
    onaut
    -0.09
    ller
    -0.09
    Ïį
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.09
    ãģĦãģĨ
    -0.09
    POSITIVE LOGITS
    æĢ§çĸ¾çĹħ
    0.10
    èĢħçļĦ
    0.10
    engers
    0.10
    OrUpdate
    0.10
    ible
    0.09
    ../
    0.09
    ä¹İ
    0.09
    ersions
    0.08
    èĢħ
    0.08
    incible
    0.08
    Activations Density 0.018%

    No Known Activations