© 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. 40937
    Prev
    Next
    INDEX
    Explanations

    Climate/geography/location

    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
    &R
    -0.31
    éĹ´çļĦ
    -0.31
    &t
    -0.28
     capsule
    -0.28
    &W
    -0.27
    æĤ±
    -0.27
    çĪ°
    -0.26
     bÃło
    -0.26
    SSERT
    -0.25
    ução
    -0.25
    POSITIVE LOGITS
    çļĦ认è¯Ĩ
    0.27
    _singleton
    0.26
    avic
    0.26
     articulated
    0.25
    åªĴä»ĭ
    0.25
    åĬ³
    0.24
    armac
    0.24
    hape
    0.24
    kaar
    0.24
    .PLL
    0.23
    Activations Density 0.108%

    No Known Activations