© 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. 27-TRANSCODER-HP
    7. 8666
    Prev
    Next
    INDEX
    Explanations

    say the ending of radi words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deep
    -0.26
    filtr
    -0.25
    座è°Ī
    -0.23
    witter
    -0.23
    åİĨåı²æĢ§
    -0.23
    ãģĦãģ£ãģŁ
    -0.23
    umpt
    -0.23
    ramework
    -0.23
    udge
    -0.23
    sit
    -0.23
    POSITIVE LOGITS
    orate
    0.27
    .Fail
    0.27
    ikon
    0.26
    iances
    0.26
    lines
    0.25
    åľ
    0.25
    çķĮçļĦ
    0.24
    纵
    0.24
    ivors
    0.24
    ivo
    0.23
    Activations Density 0.343%

    No Known Activations