© 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. 48773
    Prev
    Next
    INDEX
    Explanations

    dog

    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
    è¦Ĩ
    -0.10
    åħīæĺİ
    -0.09
    éĶĭ
    -0.09
    кÑĢа
    -0.09
    éĹ°
    -0.09
    赧
    -0.08
    пеÑĩ
    -0.08
    crease
    -0.08
     powers
    -0.08
    è¿Ļ个æŶåĢĻ
    -0.08
    POSITIVE LOGITS
    çĬ¬
    0.15
    éģĽ
    0.13
    çĭĹ
    0.13
    å®łçī©
    0.13
    çĭĹçĭĹ
    0.13
     dog
    0.12
    dog
    0.12
    Dog
    0.12
    è±¢
    0.12
    ðŁIJ¶
    0.12
    Activations Density 0.293%

    No Known Activations