© 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. 150114
    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
    æĿ¾
    -0.30
    èĩªåľ¨
    -0.30
    åĮħ
    -0.29
    åı«
    -0.28
    ondo
    -0.28
    å®ĮæĪIJ
    -0.27
    çĽĨ
    -0.27
    ä¸įèĪį
    -0.27
    æ°´
    -0.26
    宿
    -0.26
    POSITIVE LOGITS
    icode
    0.28
    微信åħ¬ä¼Ĺ
    0.27
    ologue
    0.26
    (QL
    0.25
    å¸Ĥå§Ķ
    0.25
    paralle
    0.25
    æ·¦
    0.25
    adol
    0.25
    .ld
    0.25
    çīĪæĿĥæīĢæľī
    0.24
    Activations Density 1.774%

    No Known Activations

    This feature has no known activations.