© 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. 150430
    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
    fdc
    -0.26
     Golden
    -0.24
    '):↵
    -0.24
     siden
    -0.23
    pch
    -0.23
     Independence
    -0.23
    ToWorld
    -0.23
    :');↵
    -0.23
    AxisSize
    -0.23
    ness
    -0.22
    POSITIVE LOGITS
    çļĦ人çĶŁ
    0.34
    åĩºèµĦ
    0.27
    ASIC
    0.24
    iras
    0.24
    move
    0.24
    asta
    0.23
     multiline
    0.23
     linebacker
    0.23
    å¥Ķ
    0.23
    lays
    0.22
    Activations Density 0.257%

    No Known Activations

    This feature has no known activations.