© 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. 23-TRANSCODER-HP
    7. 24016
    Prev
    Next
    INDEX
    Explanations

    German

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.34
    rium
    -0.32
    atori
    -0.31
    ä¸Ģéģĵ
    -0.26
    AVIS
    -0.26
    æĪIJåĵģ
    -0.25
    -write
    -0.25
    avis
    -0.25
    åīįæıIJ
    -0.25
    look
    -0.25
    POSITIVE LOGITS
     Displays
    0.27
     beiden
    0.25
     Renders
    0.25
    оÑĩнÑĭе
    0.25
    åħŃ大
    0.24
    WND
    0.24
     Broncos
    0.24
     braces
    0.24
     scouts
    0.24
    Migration
    0.24
    Activations Density 0.039%

    No Known Activations