© 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. 8273
    Prev
    Next
    INDEX
    Explanations

    Technical language or code snippets

    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
     [('
    -0.30
    -face
    -0.28
    ä¿Ŀ
    -0.28
    -eye
    -0.27
     sights
    -0.27
    å®Ī
    -0.27
     upon
    -0.27
    aths
    -0.26
    logs
    -0.26
     onto
    -0.26
    POSITIVE LOGITS
    ptype
    0.29
    龸éģĵ
    0.26
    æĮ½
    0.25
    ëł¥
    0.24
    urement
    0.24
    çĮ¾
    0.23
    _layers
    0.23
     uns
    0.23
    ëł¥ìĿĦ
    0.23
    çĩĬ
    0.23
    Activations Density 0.004%

    No Known Activations