© 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. 27079
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/gerund

    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
    çĮĽ
    -0.08
    ãģĦãģ¾
    -0.08
    æķ¬
    -0.08
    ấu
    -0.08
    ÙĬØ©
    -0.07
    onz
    -0.07
    /default
    -0.07
    alla
    -0.07
    ä¸įå¾Ĺå·²
    -0.07
     Boone
    -0.07
    POSITIVE LOGITS
    mez
    0.10
    å®Ľ
    0.10
     how
    0.09
    ouce
    0.09
     polo
    0.09
    æĢİä¹Īèĥ½
    0.09
    èĵĿ天
    0.09
    hoe
    0.08
    çľ¼åīįçļĦ
    0.08
    seeing
    0.08
    Activations Density 0.011%

    No Known Activations