© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    /modifying, integration, encrypted

    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
    ffee
    -0.09
    XMLElement
    -0.08
    ãģķãģ¦
    -0.08
    ombine
    -0.08
    .synthetic
    -0.08
    izont
    -0.08
    æĻĵå¾Ĺ
    -0.08
     SQLAlchemy
    -0.08
    [email
    -0.08
    ç»ıå¼Ģ
    -0.08
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.13
     other
    0.11
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    /etc
    0.09
    æ¿ĢçĥĪçļĦ
    0.09
    ifes
    0.09
    èħł
    0.09
     tháºŃm
    0.09
    phans
    0.09
    åIJĦå¼ı
    0.08
    Activations Density 0.107%

    No Known Activations