© 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. 23-TRANSCODER-HP
    7. 23588
    Prev
    Next
    INDEX
    Explanations

    apply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -blocking
    -0.29
    ç²±
    -0.27
    abyrin
    -0.27
    ORK
    -0.26
    elry
    -0.25
    imbus
    -0.25
    紧迫
    -0.25
    积æŀģä½ľçĶ¨
    -0.25
    ãģıãĤĬ
    -0.25
    ilio
    -0.24
    POSITIVE LOGITS
     outside
    0.37
    åı¯æĥ³
    0.33
     dro
    0.27
     scor
    0.27
     оÑĤлиÑĩ
    0.27
     bru
    0.26
     regard
    0.26
     Sch
    0.26
     Outside
    0.26
     load
    0.25
    Activations Density 0.149%

    No Known Activations