© 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. 10260
    Prev
    Next
    INDEX
    Explanations

    word endings for suffixes

    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
    æĦŁè§¦
    -0.10
    è¯Ĵ
    -0.09
    æĺ¯ä¸Ģéĥ¨
    -0.09
    åİ»è¿ĩ
    -0.09
    ly
    -0.09
    æ»ĭåij³
    -0.09
    åħŃ大
    -0.09
    ãģĭãģªãģĦ
    -0.09
    па
    -0.09
    ä¸ĬçĻ¾
    -0.09
    POSITIVE LOGITS
    able
    0.20
    edException
    0.17
    ised
    0.16
    ied
    0.15
    eds
    0.13
    ingly
    0.13
    edImage
    0.13
    uated
    0.12
    ado
    0.12
    edList
    0.12
    Activations Density 0.705%

    No Known Activations