© 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. 40993
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    Observ
    -0.35
    è§Ĥå¯Ł
    -0.34
     observation
    -0.34
    éĩĩéĽĨ
    -0.34
     Observ
    -0.33
     capturing
    -0.33
     survey
    -0.33
    è§Ĥæµĭ
    -0.33
     repeated
    -0.32
     probe
    -0.32
    POSITIVE LOGITS
    åĮĸè¿Ľç¨ĭ
    0.26
    autoload
    0.25
    åīįæıIJæĺ¯
    0.25
    utorials
    0.25
    _books
    0.25
    åIJĦçķĮ
    0.25
    éĥ½æľīçĿĢ
    0.24
    驹
    0.24
    lemen
    0.24
    urnished
    0.24
    Activations Density 1.343%

    No Known Activations