© 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. 30-TRANSCODER-HP
    7. 96344
    Prev
    Next
    INDEX
    Explanations

    Internet, organizations, technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĶ®
    -0.28
    æ°ª
    -0.27
    andelier
    -0.27
    æĴŃ
    -0.26
     Wend
    -0.26
    ãĥĨãĥ¼ãĥ
    -0.25
    æ¦ľ
    -0.25
    .TabStop
    -0.24
    æķĽ
    -0.24
     emple
    -0.24
    POSITIVE LOGITS
    gp
    0.26
    GP
    0.25
    anza
    0.25
    eur
    0.25
     [+
    0.24
    esti
    0.24
    sta
    0.24
    <ApplicationUser
    0.24
    äºĮ线
    0.23
    alian
    0.23
    Activations Density 0.886%

    No Known Activations