© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51988
    Prev
    Next
    INDEX
    Explanations

    pink, Pink Friday, Pink Eye

    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
    icc
    -0.10
    hti
    -0.09
    表æĥħ
    -0.09
    .stdin
    -0.09
     иÑģкÑĥÑģÑģÑĤв
    -0.09
    ffset
    -0.09
    кÑĢа
    -0.08
    itu
    -0.08
    aic
    -0.08
    ighton
    -0.08
    POSITIVE LOGITS
    erno
    0.10
    room
    0.09
    TextWriter
    0.09
    ï¸
    0.09
    ish
    0.09
    è¢Ħ
    0.09
    åĬ¡
    0.09
    ular
    0.09
    now
    0.09
    box
    0.08
    Activations Density 0.008%

    No Known Activations