© 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. 50550
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending sentences

    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
    说æĺ¯
    -0.11
    ×ķת
    -0.10
     полÑĥÑĩен
    -0.10
    istic
    -0.10
    irt
    -0.10
    ãĤĮ
    -0.09
    iler
    -0.09
    eren
    -0.09
    aub
    -0.09
    æªĶ
    -0.09
    POSITIVE LOGITS
    .au
    0.10
    ãģĤãĤĮ
    0.10
    rys
    0.10
    ãģĹãģ¾ãģĦ
    0.09
    ãģĤãĤĭç¨ĭ度
    0.08
    rug
    0.08
    åĩĮæĻ¨
    0.08
    sov
    0.08
    ries
    0.08
    -même
    0.08
    Activations Density 0.105%

    No Known Activations