© 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. 30415
    Prev
    Next
    INDEX
    Explanations

    2

    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
    èĢĹ
    -0.27
    ryn
    -0.26
    åij¨ä¸Ģ
    -0.25
    ÐĵлавнаÑı
    -0.25
    缤
    -0.25
    iddles
    -0.24
     onPostExecute
    -0.24
    åij¨
    -0.24
    BB
    -0.24
     ÑĤоваÑĢ
    -0.24
    POSITIVE LOGITS
    éĢĤæŶ
    0.28
    æĺŃ
    0.27
    ivec
    0.27
    onis
    0.26
    itel
    0.25
     Uns
    0.25
    inton
    0.25
    çŀ
    0.24
    OfClass
    0.24
    ogram
    0.24
    Activations Density 5.340%

    No Known Activations