© 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. 8568
    Prev
    Next
    INDEX
    Explanations

    license agreements

    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
    imit
    -0.32
    æľīå¤ļ大
    -0.27
     Convert
    -0.26
    builtin
    -0.26
     surtout
    -0.25
    tin
    -0.25
    åģļ强
    -0.25
    irit
    -0.24
     Conversion
    -0.24
    Conversion
    -0.24
    POSITIVE LOGITS
    æ³¢
    0.27
    ASI
    0.26
    说æĺ¯
    0.24
    Coordinator
    0.24
    客
    0.24
     labor
    0.24
     заÑĢ
    0.23
     Bray
    0.23
    ensor
    0.23
    ëıĪ
    0.23
    Activations Density 0.122%

    No Known Activations