© 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. 88271
    Prev
    Next
    INDEX
    Explanations

    Directions/Instructions

    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
    éĶĦ
    -0.31
    åı¯ä»¥æĽ´å¥½
    -0.28
    asti
    -0.26
    DataContext
    -0.26
     Sanct
    -0.25
    åıijèµ·
    -0.24
    ç®Ĺ
    -0.24
    She
    -0.24
    åı¯ä»¥çĽ´æİ¥
    -0.24
     countert
    -0.23
    POSITIVE LOGITS
    ä¸Ģä¸Ŀ
    0.28
    imeo
    0.25
    gia
    0.24
     experimentation
    0.24
    bled
    0.24
    严åİī
    0.23
     ratings
    0.23
     thorough
    0.23
     Maher
    0.23
    thal
    0.23
    Activations Density 0.057%

    No Known Activations