© 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. 40015
    Prev
    Next
    INDEX
    Explanations

    Rescuing people

    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
    éĢ¸
    -0.28
    å©Ĩ
    -0.27
    odore
    -0.27
    èĩªèº«çļĦ
    -0.26
     Ñģобой
    -0.24
    TL
    -0.24
    åıĭ
    -0.24
    amac
    -0.23
     given
    -0.23
    otypes
    -0.23
    POSITIVE LOGITS
    夫
    0.27
    æĸ°ä¸ī
    0.25
    boxing
    0.25
    æĪijåıĪ
    0.25
    eries
    0.24
    าย
    0.24
    è½°
    0.24
     flavour
    0.24
    -backed
    0.24
    enser
    0.23
    Activations Density 0.960%

    No Known Activations