© 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. 12-TRANSCODER-HP
    7. 24072
    Prev
    Next
    INDEX
    Explanations

    first/last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AndView
    -0.27
    GRA
    -0.25
    (PHP
    -0.25
    axis
    -0.25
    è§ĦèĮĥåĮĸ
    -0.25
    tol
    -0.25
    лоÑĤ
    -0.24
     sorts
    -0.24
    avity
    -0.24
     GRA
    -0.23
    POSITIVE LOGITS
    IJľç´¢
    0.27
    sequent
    0.27
    osite
    0.26
    gin
    0.26
    ninger
    0.26
    éģį
    0.25
    ensis
    0.25
    åĩłä¹İæĺ¯
    0.25
    åı·çº¿
    0.24
    osp
    0.24
    Activations Density 0.052%

    No Known Activations