© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 48177
    Prev
    Next
    INDEX
    Explanations

    Alice in wonderland, copyright, hobby japan locations

    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
    æĴ©
    -0.09
    çļĦæĦŁæĥħ
    -0.08
    ç¥Ī祷
    -0.08
    èµİ
    -0.08
    SOFTWARE
    -0.08
    æĭ¬
    -0.08
    aqu
    -0.08
    inho
    -0.08
    åħľ
    -0.08
    place
    -0.08
    POSITIVE LOGITS
    æ¸Į
    0.10
    è¯Ĺåı¥
    0.09
    IC
    0.09
    æ¯ĴæĢ§
    0.09
    æ§¿
    0.09
    è¯Ĺè¯į
    0.08
    åĨįéĢł
    0.08
    ICS
    0.08
    _COMPILER
    0.08
    copyright
    0.08
    Activations Density 0.002%

    No Known Activations