© 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. 20-TRANSCODER-HP
    7. 141754
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°°
    -0.28
    æĻ¤
    -0.27
     amet
    -0.25
    ouncy
    -0.25
    å¤§åľ°
    -0.24
     onder
    -0.24
    çľĭä¸įåĩº
    -0.24
     run
    -0.23
    触åıĬ
    -0.23
    ä¼´
    -0.23
    POSITIVE LOGITS
    izr
    0.28
    okia
    0.28
    æľīéĴĪ对æĢ§
    0.26
     confirmation
    0.25
    ä½ľ
    0.24
    产åĵģçłĶåıij
    0.24
    igation
    0.24
     Confirmation
    0.24
    liable
    0.23
    istol
    0.23
    Activations Density 2.398%

    No Known Activations