© 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. 41224
    Prev
    Next
    INDEX
    Explanations

    spill

    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
    ãĥ¼ãĥī
    -0.27
    æĻ®
    -0.27
    cono
    -0.27
    ocz
    -0.26
    arto
    -0.25
    º«
    -0.25
    _lead
    -0.25
     unus
    -0.25
    etest
    -0.25
    enis
    -0.24
    POSITIVE LOGITS
    åĨĴ
    0.30
    \Action
    0.26
    å¯ĮåIJ«
    0.25
    ows
    0.25
    æ±Łä¸ľ
    0.23
    让人们
    0.23
    \Array
    0.23
    /single
    0.23
    åIJ»
    0.23
     Rw
    0.23
    Activations Density 0.997%

    No Known Activations