© 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. 107531
    Prev
    Next
    INDEX
    Explanations

    vineyards and wine

    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
    æ·Ģ
    -0.26
     ek
    -0.26
    akter
    -0.25
     Fitzgerald
    -0.25
    æĴŀ
    -0.24
    ignet
    -0.24
    ige
    -0.23
    citation
    -0.23
    oplayer
    -0.23
    ä¸į好æĦıæĢĿ
    -0.23
    POSITIVE LOGITS
    fcc
    0.30
    æħ§
    0.25
    xhr
    0.25
    æŬ
    0.25
    fal
    0.24
    SMART
    0.24
    atching
    0.24
    าะ
    0.24
    imately
    0.24
    uchs
    0.23
    Activations Density 0.252%

    No Known Activations