© 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. 9453
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
     usefulness
    -0.28
    å¼ĢéŨ
    -0.27
     INDIRECT
    -0.27
    дол
    -0.27
     Thần
    -0.26
    anic
    -0.26
     orderId
    -0.26
    -orders
    -0.25
    tail
    -0.25
    .del
    -0.25
    POSITIVE LOGITS
     Yaz
    0.28
    ãģ¬
    0.27
    ages
    0.26
    agen
    0.25
    @qq
    0.24
     minim
    0.24
    ühr
    0.24
    èĥİ
    0.24
    棱
    0.24
    Consum
    0.23
    Activations Density 0.002%

    No Known Activations