© 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. 40697
    Prev
    Next
    INDEX
    Explanations

    for

    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
    GRESS
    -0.25
    rops
    -0.25
     @_
    -0.25
     Alley
    -0.25
    ILED
    -0.25
    è·ij
    -0.24
    DidLoad
    -0.24
    æ¯ıä½į
    -0.24
    iei
    -0.24
    æ¯ıä¸Ģä½į
    -0.24
    POSITIVE LOGITS
     external
    0.27
    ç´
    0.26
    å°ijéĩı
    0.25
     spirit
    0.25
     mse
    0.24
    åĢ¦
    0.24
    æŃ»åİ»
    0.24
     light
    0.24
    æ³¾
    0.24
    math
    0.23
    Activations Density 1.627%

    No Known Activations