© 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. 40329
    Prev
    Next
    INDEX
    Explanations

    -term

    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
    çĭIJçĭ¸
    -0.25
    å¼ĢæĪ·
    -0.25
    åĨµ
    -0.24
    centaje
    -0.24
    nj
    -0.24
    -generator
    -0.23
    curity
    -0.23
    é«ĺ楼
    -0.23
    Interval
    -0.23
    åį¯
    -0.23
    POSITIVE LOGITS
    ContentLoaded
    0.28
    ä¸ĢåĪ»
    0.27
    /Resources
    0.27
    ä¸ĩæĪ·
    0.26
    IJèĹı
    0.26
    è¡Įä¸ļåıijå±ķ
    0.26
    æĸ¹å¼ıè¿Ľè¡Į
    0.26
    ä¸įèĪį
    0.25
    orsch
    0.25
    渴
    0.25
    Activations Density 1.124%

    No Known Activations