© 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. 61766
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     doors
    -0.08
     Oriental
    -0.08
     Carnival
    -0.08
     Santo
    -0.08
    èħł
    -0.08
    _detect
    -0.08
    çħī
    -0.08
    à¤ĸ
    -0.07
    å±ıèĶ½
    -0.07
    oyer
    -0.07
    POSITIVE LOGITS
    åľ°è²Į
    0.14
    åľ°å½¢
    0.13
    åľ°çIJĨ
    0.13
    åľ°æłĩ
    0.12
    çļĦåľ°åĽ¾
    0.12
    æĻ¯è§Ĥ
    0.11
    åľ°åĽ¾
    0.11
    .getMap
    0.11
    åIJį称
    0.10
    容
    0.10
    Activations Density 0.174%

    No Known Activations