© 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. 150487
    Prev
    Next
    INDEX
    Explanations

    approach

    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
    çľĭéĩį
    -0.28
     emphas
    -0.26
    ä¼Ŀ
    -0.24
    agues
    -0.24
    åĩºä¾Ĩ
    -0.24
    ä¼łçIJĥ
    -0.23
    XC
    -0.23
    ÅĽwiad
    -0.23
    éĹ»
    -0.23
     criticised
    -0.23
    POSITIVE LOGITS
     movements
    0.28
     oneself
    0.27
     any
    0.26
    身
    0.26
    æĪ·
    0.26
     movement
    0.25
    ivirus
    0.25
     situations
    0.25
    оÑģÑĤей
    0.25
    éŀŃ
    0.24
    Activations Density 0.077%

    No Known Activations