© 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. 107893
    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
     organs
    -0.26
    åĩ¸
    -0.26
    umping
    -0.25
     evidence
    -0.25
     uncertainty
    -0.25
    ingers
    -0.25
    åĩ¹
    -0.25
    è¯ģæį®
    -0.24
     oppon
    -0.24
    uger
    -0.23
    POSITIVE LOGITS
    rape
    0.28
    \Abstract
    0.27
    ycz
    0.27
    .yahoo
    0.27
    Į¨
    0.26
    âĩĢ
    0.26
    æĬ½è±¡
    0.25
    çĻ¾åĪĨä¹ĭ
    0.25
     lxml
    0.24
    æī¾äºĨ
    0.24
    Activations Density 2.874%

    No Known Activations

    This feature has no known activations.