© 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. 53473
    Prev
    Next
    INDEX
    Explanations

    pickup trucks

    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
    çĶľç¾İ
    -0.09
    ç¾½
    -0.09
    çŃ¹
    -0.09
    åħħ
    -0.09
     car
    -0.09
    ç´§åĩij
    -0.08
    ç¾½æ¯Ľ
    -0.08
    ä¸Ģæŀļ
    -0.08
     Rey
    -0.08
    è´¨çĸij
    -0.08
    POSITIVE LOGITS
    åŁİ乡
    0.11
    çĨı
    0.10
    åį§
    0.09
    uste
    0.09
    osal
    0.09
    china
    0.09
    doc
    0.09
    Insensitive
    0.08
     Ranch
    0.08
    ald
    0.08
    Activations Density 0.073%

    No Known Activations