© 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. 34075
    Prev
    Next
    INDEX
    Explanations

    guarani and related places

    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
    alian
    -0.09
    ignon
    -0.08
    éĢĤå½ĵ
    -0.08
     Collision
    -0.08
    éĢĤ
    -0.08
    åħ¬ç¤º
    -0.08
    æŃĻ
    -0.08
    大åİħ
    -0.08
     deducted
    -0.07
    èİĨçĶ°
    -0.07
    POSITIVE LOGITS
     Rodney
    0.10
    "],"
    0.10
     Bauer
    0.10
    åĬŀäºĭ
    0.10
    .Zip
    0.09
    MOTE
    0.09
    éħĭ
    0.09
    çŀª
    0.09
    .setContent
    0.09
    ören
    0.09
    Activations Density 0.045%

    No Known Activations