© 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. 150024
    Prev
    Next
    INDEX
    Explanations

    why and how

    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
    acters
    -0.31
    iders
    -0.29
    otional
    -0.28
     spur
    -0.27
    systems
    -0.25
     signatures
    -0.25
    uations
    -0.25
    signature
    -0.24
    atures
    -0.24
    icut
    -0.24
    POSITIVE LOGITS
    soever
    0.40
    /how
    0.34
    itz
    0.32
    ?
    0.32
    doi
    0.28
    ï¼Ł
    0.28
    -ever
    0.27
     else
    0.27
    ?,
    0.27
     do
    0.27
    Activations Density 1.605%

    No Known Activations