© 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. 40616
    Prev
    Next
    INDEX
    Explanations

    Scraped or malformed 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
    Semantic
    -0.29
    ç²ĺ
    -0.27
    缣
    -0.27
    Independent
    -0.26
    okes
    -0.25
     oc
    -0.25
    rite
    -0.24
    _sem
    -0.24
    Depth
    -0.24
    badge
    -0.24
    POSITIVE LOGITS
    _formats
    0.27
    å®ŀä½ĵç»ıæµİ
    0.27
    èµĽåIJİ
    0.26
    lin
    0.25
    xec
    0.25
    dra
    0.25
    æľī趣
    0.25
    çŃ¾ä¸ĭ
    0.24
    uzz
    0.24
    æľīåĬ©
    0.24
    Activations Density 0.201%

    No Known Activations