© 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. 9087
    Prev
    Next
    INDEX
    Explanations

    marine

    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
    å°ijåĦ¿
    -0.26
     Tune
    -0.26
    æľµ
    -0.25
     atl
    -0.25
    ŀĭ
    -0.25
     tuned
    -0.24
    xFFFFFF
    -0.24
     Millions
    -0.24
    <Texture
    -0.24
    Thousands
    -0.24
    POSITIVE LOGITS
     environments
    0.38
    çݯå¢ĥä¸Ń
    0.36
    venue
    0.32
     environment
    0.32
    environments
    0.30
    çݯå¢ĥä¸ĭ
    0.29
    çݯå¢ĥ
    0.28
    ief
    0.28
     ecosystems
    0.27
    jur
    0.27
    Activations Density 0.023%

    No Known Activations