© 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. 22-TRANSCODER-HP
    7. 111462
    Prev
    Next
    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĮæł·
    -0.28
    ASS
    -0.28
    åIJĮæł·çļĦ
    -0.27
    龸çİĭ
    -0.26
     similarly
    -0.26
     ebenfalls
    -0.26
    类似çļĦ
    -0.26
     Pres
    -0.26
    ä¹ŁéĿŀ常
    -0.25
    Ass
    -0.24
    POSITIVE LOGITS
    å¥
    0.28
    cker
    0.26
    Ľå»º
    0.26
    ä¸ĩåħĥ以ä¸Ĭ
    0.25
     Defender
    0.25
    dem
    0.24
    çĢį
    0.24
     goal
    0.24
    主ä¸ļ
    0.24
    åIJ¬åIJ¬
    0.23
    Activations Density 0.005%

    No Known Activations