© 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. 62950
    Prev
    Next
    INDEX
    Explanations

    north side or end

    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
     Donovan
    -0.11
    isque
    -0.10
    esda
    -0.10
    æĦļ
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.09
    åĴĮåľ°åĮº
    -0.09
     Booth
    -0.09
    å³Ĵ
    -0.09
    ABCDEFGHI
    -0.09
    edImage
    -0.09
    POSITIVE LOGITS
    side
    0.11
    ward
    0.10
     side
    0.09
     direction
    0.09
    è¾¹
    0.09
    most
    0.09
    æĸ¹åIJij
    0.09
    wards
    0.08
     entry
    0.08
    ERIC
    0.08
    Activations Density 0.074%

    No Known Activations