© 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. 27-TRANSCODER-HP
    7. 8103
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _bases
    -0.25
    rame
    -0.24
    xFE
    -0.24
    ä¸įåŃĺåľ¨
    -0.24
    icopt
    -0.24
    ä½ľèĢħæīĢæľī
    -0.23
     <$
    -0.23
    ForResource
    -0.23
     wij
    -0.23
    (tol
    -0.23
    POSITIVE LOGITS
    åı¯èĥ½å¯¼èĩ´
    0.49
    使å¾Ĺ
    0.42
    ä¿ĥ使
    0.41
    ä¼ļå¼ķèµ·
    0.41
     causing
    0.40
    ä¼ļ使
    0.40
    å¼ķåıij
    0.39
    å¼ķèµ·
    0.38
     potentially
    0.38
     necess
    0.36
    Activations Density 0.007%

    No Known Activations