© 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. 39983
    Prev
    Next
    INDEX
    Explanations

    Mixed extracted text snippets

    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
    以å¤ĸ
    -0.37
    以åĨħ
    -0.33
     external
    -0.31
    åĨħå¤ĸ
    -0.31
    ä¹ĭå¤ĸ
    -0.30
    apan
    -0.28
     internal
    -0.26
    éĩĮ
    -0.26
     additional
    -0.26
    ä¹ĭåĨħ
    -0.26
    POSITIVE LOGITS
    åĨĻä½ľ
    0.26
    Unnamed
    0.25
    clusion
    0.25
    æ»Ł
    0.25
    æĤŃ
    0.24
    _bulk
    0.24
    aspers
    0.24
    ино
    0.24
    ç®Ģ称
    0.24
    SelectionMode
    0.23
    Activations Density 1.051%

    No Known Activations