© 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. 24-TRANSCODER-HP
    7. 150048
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī½
    -0.24
     Cover
    -0.24
    baugh
    -0.24
    è¦Ĩ
    -0.24
    olg
    -0.24
    æ±ĩæĢ»
    -0.23
     divisive
    -0.23
    urers
    -0.23
    DU
    -0.22
    resses
    -0.22
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸ģ
    0.26
    stk
    0.26
    abilidade
    0.25
     similarly
    0.25
    Similarly
    0.25
     deÄŁerl
    0.24
    èĮ¬
    0.24
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    0.23
    念
    0.23
    OfDay
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.