© 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. 40459
    Prev
    Next
    INDEX
    Explanations

    membrane

    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
    æĭĹ
    -0.30
    ographies
    -0.28
    licative
    -0.26
    WithError
    -0.26
    ç³ľ
    -0.25
    è¾ľè´Ł
    -0.25
    涯
    -0.24
    AndView
    -0.24
    eree
    -0.24
    _perms
    -0.24
    POSITIVE LOGITS
    æĿŁ
    0.28
    赶
    0.24
     menos
    0.24
    alu
    0.24
    nc
    0.24
     Illustr
    0.23
    Above
    0.23
    /owl
    0.23
     Hits
    0.23
    /videos
    0.23
    Activations Density 1.027%

    No Known Activations