© 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. 39700
    Prev
    Next
    INDEX
    Explanations

    interdisciplinary, operative, faculty, interests

    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
    /her
    -0.11
    nel
    -0.11
    ãģ®ãģ¯
    -0.10
    sWith
    -0.10
    -0.10
    ãģŁãĤģãģ«
    -0.10
    sa
    -0.10
    scape
    -0.09
    ãģ»ãģĨ
    -0.09
    sd
    -0.08
    POSITIVE LOGITS
    eing
    0.12
    ization
    0.12
    æĢ§å¼º
    0.11
    polation
    0.11
    prising
    0.10
    stitial
    0.10
    åĮĸçļĦ
    0.10
    isation
    0.10
    most
    0.10
    ize
    0.10
    Activations Density 0.031%

    No Known Activations