© 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. 22145
    Prev
    Next
    INDEX
    Explanations

    cow's or cows' related

    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
    ively
    -0.11
    ©
    -0.10
     kiá»ĩn
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    onica
    -0.09
    hift
    -0.08
    ugen
    -0.08
    SingleNode
    -0.08
    undi
    -0.08
    æĹłç©·
    -0.08
    POSITIVE LOGITS
    boys
    0.11
    çĬĬ
    0.10
    ards
    0.10
    rig
    0.10
    aday
    0.10
    cul
    0.10
    æ±IJ
    0.10
    iliar
    0.10
    hide
    0.09
    yled
    0.09
    Activations Density 0.013%

    No Known Activations