© 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. 57117
    Prev
    Next
    INDEX
    Explanations

    pil

    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
     decay
    -0.28
     heir
    -0.28
     inse
    -0.25
     disappearance
    -0.25
    对ä¸įèµ·
    -0.25
    pread
    -0.24
    _GAP
    -0.24
    è¡°
    -0.24
     peter
    -0.23
     Insight
    -0.23
    POSITIVE LOGITS
    aries
    0.28
    arian
    0.27
    rn
    0.26
    arians
    0.26
    çļĦä¸Ģ款
    0.26
     Cmd
    0.26
    rab
    0.25
    WARD
    0.25
    å¿«
    0.25
    å¼Ģåĩº
    0.25
    Activations Density 0.019%

    No Known Activations