© 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. 57442
    Prev
    Next
    INDEX
    Explanations

    Technical writing and community

    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
     join
    -0.72
    åĬłåħ¥
    -0.66
    join
    -0.66
    群ä½ĵ
    -0.64
     joined
    -0.64
    è¡ĮåĪĹ
    -0.63
     group
    -0.61
    Join
    -0.60
     joining
    -0.60
     Join
    -0.59
    POSITIVE LOGITS
    ChangedEventArgs
    0.25
     Labs
    0.24
    atures
    0.24
     facility
    0.24
    ä¸ķ
    0.24
    å¤ļåľ°
    0.24
    aken
    0.23
    dao
    0.23
    eday
    0.23
    .bp
    0.23
    Activations Density 0.003%

    No Known Activations