© 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. 29884
    Prev
    Next
    INDEX
    Explanations

    melbourne

    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
    åĢĮ
    -0.27
    recursive
    -0.27
    caa
    -0.26
    åļ¼
    -0.26
    O
    -0.26
    æ¿Ģåħī
    -0.25
    itter
    -0.25
    æĢĻ
    -0.25
    ÑĤеÑĢ
    -0.25
    mma
    -0.24
    POSITIVE LOGITS
     disc
    0.29
    false
    0.27
    bole
    0.26
    Bring
    0.26
     discs
    0.26
     false
    0.26
    åºĬä¸Ĭ
    0.25
    .false
    0.25
    edis
    0.25
    hue
    0.25
    Activations Density 1.933%

    No Known Activations