© 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. 8558
    Prev
    Next
    INDEX
    Explanations

    IGHT

    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
    æĮ¤
    -0.28
    æľīæĿĥ
    -0.26
     Tomorrow
    -0.26
    /tool
    -0.26
    è¯Ħä»·
    -0.25
    payload
    -0.24
    æįı
    -0.24
    encil
    -0.24
     ahead
    -0.24
    éĶ¦
    -0.24
    POSITIVE LOGITS
    æݧåĪ¶ç³»ç»Ł
    0.27
    /rs
    0.26
    controlled
    0.26
    ä¸įæĸŃæıIJé«ĺ
    0.25
     molecule
    0.25
    esco
    0.25
     circuits
    0.24
     newText
    0.24
     chemical
    0.24
    æ°Ĺ
    0.24
    Activations Density 0.001%

    No Known Activations