© 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. 9-TRANSCODER-HP
    7. 29714
    Prev
    Next
    INDEX
    Explanations

    FTP servers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amed
    -0.29
    GBT
    -0.28
    cott
    -0.27
     GUIDE
    -0.25
    urst
    -0.24
    تÙħ
    -0.24
    entially
    -0.24
    èĸ
    -0.24
    ellan
    -0.24
    åĪĴ
    -0.24
    POSITIVE LOGITS
    å°¼äºļ
    0.26
    ä¸įè´Ł
    0.25
    æĦ
    0.25
    åĭ¢
    0.25
    isto
    0.25
    åħ¥éĢī
    0.24
     presenting
    0.24
    èĪĨ
    0.24
    rä
    0.24
    IRR
    0.24
    Activations Density 1.245%

    No Known Activations