© 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. 36171
    Prev
    Next
    INDEX
    Explanations

    trip, tripadvisor, assignment

    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
    uar
    -0.10
    вл
    -0.09
    reon
    -0.09
    çķ¸
    -0.09
    oons
    -0.09
    âĺ°
    -0.09
     divis
    -0.09
    oins
    -0.09
    OUN
    -0.09
    Appear
    -0.09
    POSITIVE LOGITS
    å¾ľ
    0.09
    ãģĦãģĭ
    0.09
    net
    0.08
    ple
    0.08
    pled
    0.08
    è¡Įç¨ĭ
    0.08
     marin
    0.08
    éĩįéĩį
    0.08
    доб
    0.08
    wire
    0.08
    Activations Density 0.009%

    No Known Activations