© 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. 19336
    Prev
    Next
    INDEX
    Explanations

    wolf, wolves, werewolf, lupus

    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
    èĬ¥
    -0.10
    å±IJ
    -0.09
    çŃĶ
    -0.09
    ä¹Ļ
    -0.09
    oro
    -0.08
    ToDevice
    -0.08
    榨
    -0.08
    è¾Ľè¾£
    -0.08
    éĩijåŃĹ
    -0.08
     Palm
    -0.08
    POSITIVE LOGITS
    wolf
    0.13
    åĹ¥
    0.12
    çĭ¼
    0.12
     wolf
    0.12
    ðŁIJº
    0.11
    çĭĪ
    0.11
    åļİ
    0.10
     wolves
    0.10
    è±ķ
    0.09
    è£ĺ
    0.09
    Activations Density 0.066%

    No Known Activations