© 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. 25-TRANSCODER-HP
    7. 107660
    Prev
    Next
    INDEX
    Explanations

    Physical measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮĻ
    -0.27
    级åĪ«çļĦ
    -0.26
    adal
    -0.26
    -legged
    -0.25
    -level
    -0.25
    dot
    -0.25
     linked
    -0.25
     LINK
    -0.25
    ulers
    -0.24
    -length
    -0.24
    POSITIVE LOGITS
    éļĨ
    0.31
    пÑĢеÑģÑģ
    0.28
     ká»ĭp
    0.28
    ouve
    0.27
    infeld
    0.26
    æĶ¾å¤§
    0.24
    æį¡
    0.24
    âĪ
    0.24
    unting
    0.24
    ản
    0.24
    Activations Density 0.979%

    No Known Activations