© 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. 14-TRANSCODER-HP
    7. 41424
    Prev
    Next
    INDEX
    Explanations

    Questions and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *(-
    -0.28
    åĺĽ
    -0.27
    ensitivity
    -0.27
    arya
    -0.26
    é»
    -0.25
     Northwestern
    -0.24
     khắc
    -0.23
    ucked
    -0.23
     uniquely
    -0.23
     screwed
    -0.22
    POSITIVE LOGITS
     healthy
    0.27
    ÑģÑĤеÑĢ
    0.26
    bies
    0.26
    cono
    0.25
     Fel
    0.25
    å®Įåħ¨
    0.24
    coni
    0.24
    /pass
    0.24
     vocab
    0.24
     char
    0.24
    Activations Density 0.093%

    No Known Activations