© 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. 150022
    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
    ê²½
    -0.29
    壤
    -0.26
    elling
    -0.26
    å±Ĥåĩºä¸įç©·
    -0.25
     Bradley
    -0.25
    æ¡ħ
    -0.24
    _baseline
    -0.24
    å¿łå®ŀ
    -0.24
     Crowd
    -0.23
    以ä¸Ĭ
    -0.23
    POSITIVE LOGITS
    æµģè¡ĮçļĦ
    0.25
    èļĤ
    0.25
     cut
    0.24
    ILED
    0.24
     impl
    0.24
    Transformation
    0.23
    åĬĪ
    0.23
    æĸ°è§Ħ
    0.23
     CUT
    0.23
    .testng
    0.23
    Activations Density 0.090%

    No Known Activations

    This feature has no known activations.