© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7491
    Prev
    Next
    INDEX
    Explanations

    shopping malls, centers, cart

    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
    ìĤ¬íķŃ
    -0.11
    ureka
    -0.10
    IRST
    -0.09
    uz
    -0.09
    äºĨèĩªå·±çļĦ
    -0.09
    lessly
    -0.09
    orses
    -0.08
    .sb
    -0.08
     pil
    -0.08
    rimon
    -0.08
    POSITIVE LOGITS
    reads
    0.11
    PING
    0.10
    igli
    0.10
    缨
    0.09
    ilon
    0.09
    од
    0.09
    .Mutable
    0.09
    bed
    0.09
    line
    0.08
    forced
    0.08
    Activations Density 0.008%

    No Known Activations