© 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. 12-TRANSCODER-HP
    7. 23827
    Prev
    Next
    INDEX
    Explanations

    cellular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Convention
    -0.26
    ç²¢
    -0.26
    åįıå®ļ
    -0.25
    ä¸ĭ游
    -0.25
     Summit
    -0.25
    rome
    -0.25
    çķĶ
    -0.24
    çĦ¦
    -0.24
    /Branch
    -0.24
    exemple
    -0.24
    POSITIVE LOGITS
    hana
    0.28
    анÑģ
    0.26
     Static
    0.26
     Mat
    0.26
     seam
    0.25
    anner
    0.25
     Economy
    0.25
    atts
    0.25
    éļ§
    0.24
    纽
    0.24
    Activations Density 0.004%

    No Known Activations