© 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. 149601
    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
    亡
    -0.31
    inz
    -0.29
    å·½
    -0.26
    apr
    -0.26
    à¸ĸ
    -0.25
     hu
    -0.25
     uncert
    -0.25
     kém
    -0.25
    setDefault
    -0.25
    ãĥ«ãĥī
    -0.24
    POSITIVE LOGITS
    ä¹ĭä¸Ĭ
    0.26
    itizen
    0.26
     Eastern
    0.24
    assel
    0.24
    -East
    0.24
    adj
    0.24
     *"
    0.23
     filmy
    0.23
    Eastern
    0.23
     NSMutable
    0.23
    Activations Density 1.429%

    No Known Activations

    This feature has no known activations.