© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    one another

    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
    ends
    -0.12
    Ìģ
    -0.12
    ×ķת
    -0.12
    otle
    -0.10
    ات
    -0.10
    ened
    -0.09
    halb
    -0.09
    оÑĤ
    -0.09
    ties
    -0.09
     zwar
    -0.09
    POSITIVE LOGITS
    ãģĤãĤĭ
    0.11
    çĦ¶æĺ¯
    0.11
    媳
    0.11
    ello
    0.11
    ãģĤãĤĭç¨ĭ度
    0.10
    каÑĤ
    0.09
    åĽŀäºĭ
    0.09
     dolayı
    0.09
    odel
    0.09
    ÑĪим
    0.09
    Activations Density 0.020%

    No Known Activations