© 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. 57235
    Prev
    Next
    INDEX
    Explanations

    Code/non-natural language text

    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
     may
    -0.52
     might
    -0.43
    may
    -0.40
     May
    -0.40
    May
    -0.38
    might
    -0.37
    åı¯èĥ½ä¼ļ
    -0.35
    åı¯èĥ½
    -0.35
     Might
    -0.30
     MAY
    -0.28
    POSITIVE LOGITS
    olla
    0.27
    ãģªãģĦãģ§ãģĻ
    0.24
     debating
    0.24
     tomb
    0.24
    _Des
    0.23
    .ibatis
    0.23
    .Accessible
    0.23
     treasury
    0.23
     Demp
    0.23
    éģĭ
    0.23
    Activations Density 0.001%

    No Known Activations