© 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. 51235
    Prev
    Next
    INDEX
    Explanations

    Morgedal and Morgenthau

    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
    er
    -0.19
    ings
    -0.19
    lah
    -0.17
    ments
    -0.15
    ment
    -0.14
    åĦ¿
    -0.14
    ly
    -0.14
    edException
    -0.13
    edImage
    -0.13
    edList
    -0.12
    POSITIVE LOGITS
    a
    0.13
    olume
    0.13
    า
    0.12
    ãĥ¼
    0.12
    Ø©
    0.10
    aÄŁ
    0.10
    ãģŁãĤģãģ«
    0.10
    æĺ¯å¤ļä¹Ī
    0.10
    а
    0.10
    åľ¨
    0.10
    Activations Density 0.411%

    No Known Activations