© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40637
    Prev
    Next
    INDEX
    Explanations

    Code related text

    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
     partic
    -0.27
    èĩ³å°ij
    -0.26
    ax
    -0.26
    otec
    -0.25
     Ax
    -0.25
    Except
    -0.25
    åĩĢ
    -0.24
    æĮĩçĤ¹
    -0.24
    çĥŁ
    -0.24
    ä¸Ĭç½ij
    -0.24
    POSITIVE LOGITS
    Deal
    0.27
     Ged
    0.27
    ç±³ç²ī
    0.25
     }},↵
    0.25
    æijģ
    0.25
     operator
    0.24
    slashes
    0.24
    roat
    0.24
    intree
    0.24
    çłĶ究éĻ¢
    0.23
    Activations Density 0.356%

    No Known Activations