© 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. 57470
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
     anonymously
    -0.29
    ivot
    -0.27
    otted
    -0.27
    .cx
    -0.26
     resurrect
    -0.26
     cab
    -0.25
     seal
    -0.25
    å²ģ以ä¸ĭ
    -0.25
    bei
    -0.24
    å°ģ
    -0.24
    POSITIVE LOGITS
    彩
    0.29
    èĵĿåĽ¾
    0.28
    ç»ĨåĮĸ
    0.27
    preter
    0.26
    å±ł
    0.26
    åĪļéľĢ
    0.26
    etal
    0.26
    inium
    0.25
    è²Į
    0.25
    è¯Ń
    0.24
    Activations Density 0.817%

    No Known Activations