© 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. 9-TRANSCODER-HP
    7. 30205
    Prev
    Next
    INDEX
    Explanations

    Psychology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    OI
    -0.26
    ños
    -0.26
    ortex
    -0.26
     Material
    -0.26
    material
    -0.26
    ç¿İ
    -0.25
    æİ¥åĪ°
    -0.25
    verbosity
    -0.24
    SOC
    -0.24
    积累
    -0.24
    POSITIVE LOGITS
    itarian
    0.28
    åŃª
    0.27
     ruta
    0.25
     concurrently
    0.25
     Duffy
    0.25
    åĩłå¼ł
    0.25
     threaded
    0.25
    Expose
    0.25
    票
    0.24
    Principal
    0.24
    Activations Density 0.280%

    No Known Activations