© 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. 108550
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     cogn
    -0.26
    WK
    -0.26
    åłĥ
    -0.25
    齿
    -0.24
     soci
    -0.24
    çĽ¸äº²
    -0.24
    æīĢæıIJä¾ĽçļĦ
    -0.24
     Rossi
    -0.23
    çĽ¸å¹²
    -0.23
    stretch
    -0.23
    POSITIVE LOGITS
    ingular
    0.28
    ill
    0.27
    alt
    0.25
     nämlich
    0.25
    otta
    0.25
    entication
    0.24
    Lets
    0.24
    è¿Ļè¯Ŀ
    0.24
    说åĪ°
    0.24
    ille
    0.24
    Activations Density 0.937%

    No Known Activations