© 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. 23304
    Prev
    Next
    INDEX
    Explanations

    Homeland

    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
    Chip
    -0.28
    èĬĿ
    -0.27
     competit
    -0.26
    åĩºèī²
    -0.26
    utm
    -0.26
    ä»İåīį
    -0.25
    errar
    -0.24
    éĮ¢
    -0.24
    çģ¾åĮº
    -0.24
    prevState
    -0.23
    POSITIVE LOGITS
    HING
    0.28
    èĤĩ
    0.24
    (↵↵
    0.24
    Everybody
    0.24
     everybody
    0.24
    åĬ¡
    0.24
     McKay
    0.24
    AGAIN
    0.24
    clock
    0.23
     ranked
    0.23
    Activations Density 0.030%

    No Known Activations