© 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. 40198
    Prev
    Next
    INDEX
    Explanations

    Data processing and 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
     tod
    -0.28
     pitches
    -0.27
     concern
    -0.27
     Shore
    -0.25
     scram
    -0.25
    人çļĦ
    -0.25
    cran
    -0.25
    çīĪæĿĥæīĢæľī
    -0.25
     manip
    -0.25
     leg
    -0.24
    POSITIVE LOGITS
    <tr
    0.27
    çĥŁèĬ±
    0.27
    ä¸Ģ个å¤ļ
    0.26
    èĥª
    0.26
    __.__
    0.25
     setPosition
    0.25
     hj
    0.24
    ifty
    0.24
    ä¸ī项
    0.24
    ëĶ°
    0.24
    Activations Density 0.889%

    No Known Activations