© 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. 5265
    Prev
    Next
    INDEX
    Explanations

    emergency services departments

    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
    èĮ«
    -0.08
     Neb
    -0.08
     guest
    -0.08
    rame
    -0.08
    æĹ©å°±
    -0.08
    æĭ¥
    -0.08
    为äºĨ让
    -0.08
    å¾ģæľį
    -0.07
    _dot
    -0.07
     thái
    -0.07
    POSITIVE LOGITS
    åĢ¼å®Ī
    0.16
    åĢ¼çıŃ
    0.15
    åºĶæĢ¥
    0.13
    åij¼åı«
    0.12
    åħ¨å¤©
    0.12
     emergency
    0.12
    ç´§æĢ¥
    0.12
    çĶµè¯Ŀ
    0.12
    emergency
    0.12
    Emergency
    0.11
    Activations Density 0.113%

    No Known Activations