© 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. 40636
    Prev
    Next
    INDEX
    Explanations

    ANC and ancient

    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
    -dot
    -0.29
    èĤ¼
    -0.27
    _LANG
    -0.26
    fcc
    -0.25
    DEV
    -0.25
    expl
    -0.25
     unstable
    -0.25
    ilan
    -0.24
     dev
    -0.24
    arov
    -0.24
    POSITIVE LOGITS
    ^K
    0.32
    æĪijè¿ĺ
    0.29
    æĪijå¸ĮæľĽ
    0.27
    æĢ»ä»·
    0.25
    æĹ¢æľī
    0.25
    éĻIJ
    0.24
    ()?
    0.24
    <<(
    0.24
     dequeue
    0.24
     topics
    0.23
    Activations Density 0.940%

    No Known Activations