© 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. 41391
    Prev
    Next
    INDEX
    Explanations

    End of sentence/code

    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
    ActionTypes
    -0.28
    CharArray
    -0.27
    outil
    -0.26
    åIJĮå¿ĥ
    -0.25
     improved
    -0.25
    uit
    -0.25
    ogan
    -0.24
    otec
    -0.24
    æĶ¹èī¯
    -0.24
     gal
    -0.24
    POSITIVE LOGITS
    ếu
    0.27
    recision
    0.25
    ck
    0.25
    æİĩ
    0.25
    åįģä¸īå±Ĭ
    0.25
    ãĤıãģij
    0.24
    çŁ¥éģĵèĩªå·±
    0.24
    /provider
    0.24
    éĩįéĩı
    0.24
    缴è¾ĸ
    0.24
    Activations Density 0.565%

    No Known Activations