© 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. 9213
    Prev
    Next
    INDEX
    Explanations

    7

    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
    离
    -0.28
     trom
    -0.27
    MEDIA
    -0.27
    arf
    -0.27
    æ¡¡
    -0.27
    称ä¹ĭ
    -0.25
    åij½ä¸Ń
    -0.25
     knocks
    -0.23
     vests
    -0.23
    å¸ĥ
    -0.23
    POSITIVE LOGITS
     Spectrum
    0.29
    oot
    0.28
    _many
    0.27
     allo
    0.26
     approving
    0.26
    æķĽ
    0.26
    ண
    0.24
    ither
    0.24
    å¥ĸåѦéĩij
    0.24
    çĶij
    0.24
    Activations Density 0.874%

    No Known Activations