© 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. 150890
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    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
    lopedia
    -0.30
    ÃŃch
    -0.28
    åı¸
    -0.26
    ISIBLE
    -0.25
    izona
    -0.25
    ensible
    -0.24
     responsibly
    -0.24
    iki
    -0.24
    IGH
    -0.23
    (assign
    -0.23
    POSITIVE LOGITS
    ç´§å¼ł
    0.36
    åĺĪ
    0.31
    é«ĺ温
    0.31
     stressed
    0.30
    Under
    0.29
     crowded
    0.29
     Under
    0.29
    èľ·
    0.29
    çĸ²åĬ³
    0.29
     under
    0.28
    Activations Density 0.929%

    No Known Activations