© 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. 150098
    Prev
    Next
    INDEX
    Explanations

    unusual words

    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
     specialized
    -0.29
    å¤
    -0.29
     specialization
    -0.29
    issors
    -0.28
     consistency
    -0.27
     secrecy
    -0.27
    æ³ķåĽ½
    -0.26
    ά
    -0.26
     specializing
    -0.26
    å°ģ建
    -0.24
    POSITIVE LOGITS
     begr
    0.32
    daq
    0.27
    éĵº
    0.26
    PRINTF
    0.26
    èħ±
    0.25
    tin
    0.25
     blew
    0.24
    åģļçļĦ
    0.24
     maté
    0.24
     QGraphics
    0.24
    Activations Density 0.956%

    No Known Activations