© 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. 150967
    Prev
    Next
    INDEX
    Explanations

    spending

    np_max-act-logits · gemini-2.0-flash
    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
    ooth
    -0.29
    apest
    -0.29
    hound
    -0.28
    aley
    -0.27
    pan
    -0.27
    anka
    -0.26
     Broken
    -0.26
    letics
    -0.25
     Pan
    -0.25
     pan
    -0.25
    POSITIVE LOGITS
    _ALLOC
    0.29
     undertaking
    0.27
     dominated
    0.26
    R
    0.26
    ç´
    0.26
     Thomson
    0.25
    Ra
    0.24
     Undert
    0.24
    RM
    0.24
     carrying
    0.23
    Activations Density 0.558%

    No Known Activations