© 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. 25-TRANSCODER-HP
    7. 108225
    Prev
    Next
    INDEX
    Explanations

    teach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érique
    -0.26
    -hero
    -0.26
    丸
    -0.24
    ');?>↵
    -0.24
    _SYMBOL
    -0.24
    asters
    -0.24
    iola
    -0.24
     Bieber
    -0.23
    PHPExcel
    -0.23
     Gap
    -0.23
    POSITIVE LOGITS
    被人
    0.28
    èIJ½ä¸ĭ
    0.27
     esk
    0.27
    èĥĮéĿ¢
    0.27
    让åŃ©åŃIJ
    0.26
    åħ¬åħ±èµĦæºIJ
    0.26
     mh
    0.26
    交æį¢
    0.25
    å¾ģæ±Ĥ
    0.25
     forgotten
    0.25
    Activations Density 0.938%

    No Known Activations