© 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. 63868
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    mach
    -0.28
    _UNIX
    -0.27
    OOT
    -0.27
    loo
    -0.25
    bane
    -0.25
    OO
    -0.24
    æ³ķå¾ĭè§Ħå®ļ
    -0.24
    éĿŀ常å¤ļçļĦ
    -0.24
    åįĹæĸ¹
    -0.24
    å½ĵåľ°çļĦ
    -0.24
    POSITIVE LOGITS
    æİĴè¡Į
    0.25
    öl
    0.25
    产ä¸ļ
    0.25
     PCM
    0.24
    æīĵäºĨ
    0.24
     self
    0.24
     Tit
    0.23
    esse
    0.23
    idden
    0.23
    yme
    0.23
    Activations Density 57.726%

    No Known Activations