© 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. 20956
    Prev
    Next
    INDEX
    Explanations

    .com, .co, Realty

    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
    å¿ĥæĥħ
    -0.11
     Svens
    -0.10
    åĵªæĢķ
    -0.09
    èĤł
    -0.09
    人ä½ĵ
    -0.08
    åĩ»æĿĢ
    -0.08
    strup
    -0.08
    undle
    -0.08
    æ©¡èĥ¶
    -0.08
    .setView
    -0.08
    POSITIVE LOGITS
    dent
    0.09
    ç»°
    0.09
    nth
    0.09
    æIJŃ
    0.08
    ä¸Ģ群人
    0.08
    æĿĪ
    0.08
    梢
    0.08
     ÑģлÑĥÑĩа
    0.08
    /reference
    0.08
    å¤Ħå¤Ħ
    0.08
    Activations Density 0.001%

    No Known Activations