© 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. 41096
    Prev
    Next
    INDEX
    Explanations

    transportation

    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
    Blockly
    -0.31
    riger
    -0.26
    roman
    -0.26
    æ½ľæ°´
    -0.26
    èµ°å¾Ĺ
    -0.25
    ikal
    -0.25
     greedy
    -0.25
    榷
    -0.25
    导èĪª
    -0.24
    转载
    -0.24
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.30
     plain
    0.29
    ampton
    0.27
     HomeComponent
    0.26
    Paper
    0.26
    çĻ»åħ¥
    0.26
    æĪIJ份
    0.26
    .onDestroy
    0.25
    对æĪij说
    0.24
    NESS
    0.24
    Activations Density 1.142%

    No Known Activations