© 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. 150798
    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
    è¿ŀ线
    -0.28
     differential
    -0.27
    PLICATE
    -0.26
     Formation
    -0.25
    าà¸ĩ
    -0.24
     observer
    -0.24
    -aff
    -0.24
     Differential
    -0.23
    åĪĨåĪ«ä¸º
    -0.23
     reader
    -0.23
    POSITIVE LOGITS
    crap
    0.27
    åIJĮèĥŀ
    0.26
    ôm
    0.26
    anca
    0.25
    msgid
    0.24
    meld
    0.24
    (bounds
    0.24
    ãng
    0.24
    elo
    0.24
    pdata
    0.24
    Activations Density 0.170%

    No Known Activations

    This feature has no known activations.