© 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. 107750
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    abouts
    -0.29
    htable
    -0.27
    uft
    -0.26
     metic
    -0.25
    inals
    -0.25
    bü
    -0.25
    enberg
    -0.25
    Dict
    -0.25
    æįº
    -0.24
     TL
    -0.24
    POSITIVE LOGITS
     genders
    0.29
    ä¸İåIJ¦
    0.28
     graz
    0.26
    çīĪ
    0.26
    è´¹
    0.25
    vy
    0.25
     societies
    0.25
     voices
    0.24
    稿
    0.24
     conjug
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.