© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149416
    Prev
    Next
    INDEX
    Explanations

    announcements, demands, promises

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ãģĵãģ¨ãģ§ãģĻ
    -0.30
     полÑĮзÑĥ
    -0.29
    ä¹ĭäºĭ
    -0.28
     Meth
    -0.27
    opro
    -0.25
    åħļæĢ»
    -0.25
    ãĤĭãĤĤãģ®
    -0.25
    ayas
    -0.25
    ouflage
    -0.25
    ä¼ģä¸ļåĴĮ
    -0.24
    POSITIVE LOGITS
    ner
    0.31
    幺
    0.30
    ging
    0.28
    æµĭ
    0.28
    çĤ½
    0.26
    roph
    0.26
    ä¸Ģ线
    0.25
    ring
    0.25
    [
    0.25
    qc
    0.24
    Activations Density 0.970%

    No Known Activations