© 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. 23594
    Prev
    Next
    INDEX
    Explanations

    record

    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
    è¯ģ
    -0.29
    side
    -0.28
     Lives
    -0.27
    åĶ¤
    -0.27
    Validation
    -0.26
    lique
    -0.26
    ervation
    -0.26
    ä¹ĥ
    -0.25
    ensive
    -0.25
     Testament
    -0.24
    POSITIVE LOGITS
    coles
    0.25
    äºĮæ°§åĮĸ碳
    0.25
     audiences
    0.25
    æĬĦ
    0.25
    æĥħ
    0.24
     Ago
    0.24
    izr
    0.24
    edBy
    0.24
    icity
    0.23
    ByEmail
    0.23
    Activations Density 0.007%

    No Known Activations