© 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. 29305
    Prev
    Next
    INDEX
    Explanations

    long

    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
     surface
    -0.29
    ate
    -0.26
    atif
    -0.26
     Hast
    -0.25
    arat
    -0.25
     speaking
    -0.25
    urf
    -0.25
    说è¯Ŀ
    -0.24
    èĿĩ
    -0.24
    ÅŁa
    -0.24
    POSITIVE LOGITS
    åİĨå¹´
    0.29
    berger
    0.27
    ECH
    0.27
    iddle
    0.27
    etro
    0.26
     True
    0.25
     каÑĩ
    0.25
    True
    0.25
    IFORM
    0.25
    adero
    0.25
    Activations Density 0.794%

    No Known Activations