© 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. 24-TRANSCODER-HP
    7. 150815
    Prev
    Next
    INDEX
    Explanations

    say "al" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.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¤ĩ
    -0.28
    frei
    -0.28
    essen
    -0.26
    /etc
    -0.26
    åľ°ä¸Ń
    -0.25
    ä¹ĭ家
    -0.25
    ä¸Ģæł·çļĦ
    -0.24
    çħ
    -0.24
    读åIJİ
    -0.24
    ::*
    -0.24
    POSITIVE LOGITS
     Securities
    0.28
    itter
    0.28
    ValueChanged
    0.27
    armed
    0.27
     al
    0.27
    illis
    0.26
     Robinson
    0.26
    urent
    0.25
    urg
    0.24
    UED
    0.24
    Activations Density 0.634%

    No Known Activations