© 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. 40759
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    å°¼äºļ
    -0.28
    esture
    -0.28
    ISTRY
    -0.27
    heets
    -0.27
    ewear
    -0.26
     stretched
    -0.26
    oteca
    -0.25
    _ft
    -0.25
     Torch
    -0.25
    urname
    -0.25
    POSITIVE LOGITS
    æĹĮ
    0.28
     Äijêm
    0.27
    qb
    0.27
    æįķæįī
    0.27
    adero
    0.26
    éĩĩæijĺ
    0.25
    èıľé¸Ł
    0.25
    unte
    0.25
    à¤ł
    0.24
     summed
    0.24
    Activations Density 1.741%

    No Known Activations