© 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. 39730
    Prev
    Next
    INDEX
    Explanations

    Israel

    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
    tract
    -0.27
    æĪij们çļĦ
    -0.27
    .axes
    -0.26
    æ±Ĥ
    -0.26
    èĴ¸æ±½
    -0.25
    ç¼ķ
    -0.25
    åĴ«
    -0.25
    .asp
    -0.25
    .struts
    -0.24
    æ»ļæ»ļ
    -0.24
    POSITIVE LOGITS
    uty
    0.28
    oir
    0.27
     VIR
    0.25
    gons
    0.25
    lli
    0.25
     PropertyInfo
    0.25
    ournaments
    0.25
    (nc
    0.25
    ware
    0.24
    模èĮĥ
    0.24
    Activations Density 3.563%

    No Known Activations