© 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. 57707
    Prev
    Next
    INDEX
    Explanations

    schools

    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
    roids
    -0.26
     predecessors
    -0.26
    çĶ·ç¥ŀ
    -0.25
     Gra
    -0.24
     mocks
    -0.24
    èĽĢ
    -0.24
     directors
    -0.24
    peria
    -0.24
    antics
    -0.23
    scenes
    -0.23
    POSITIVE LOGITS
     Lis
    0.24
    alem
    0.23
    ucid
    0.23
    æľĢ
    0.23
    ä¸Ńåįİ
    0.23
    ÙĪرÙĪ
    0.23
    å¦Ĥ
    0.23
    çŁ³å¤´
    0.23
    flamm
    0.22
    ষ
    0.22
    Activations Density 0.013%

    No Known Activations