© 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. 29383
    Prev
    Next
    INDEX
    Explanations

    Cutting in half

    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
    preneur
    -0.27
    InputStream
    -0.26
    绳
    -0.25
     diy
    -0.25
    vig
    -0.25
    èĩªçĦ¶
    -0.25
     Mut
    -0.24
    heets
    -0.24
    ETER
    -0.24
    bul
    -0.24
    POSITIVE LOGITS
     pepp
    0.25
    çĮ«
    0.25
    angelog
    0.24
    å°ıçĻ½
    0.24
    cad
    0.23
    沸
    0.23
    é¼ł
    0.23
    äºĨè¿ĩæĿ¥
    0.23
     pets
    0.23
     sob
    0.23
    Activations Density 0.368%

    No Known Activations