© 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. 55551
    Prev
    Next
    INDEX
    Explanations

    already

    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
    sWith
    -0.11
    ä¸įåĩĨ
    -0.11
    iture
    -0.10
    ç»Īäºİ
    -0.10
    忽çĦ¶
    -0.10
    ographer
    -0.10
    ãģĿãĤĤãģĿãĤĤ
    -0.10
    ä¸ĢæŦ
    -0.10
    lessly
    -0.10
    ç«ĭåį³
    -0.10
    POSITIVE LOGITS
    åĬłä¹ĭ
    0.09
    ç»ıéĶĢ
    0.09
    çĸ£
    0.08
    ché
    0.08
     давно
    0.08
    èĩ»
    0.08
    tics
    0.08
    ts
    0.08
    gest
    0.08
    âĶĮ
    0.08
    Activations Density 0.016%

    No Known Activations