© 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. 24-TRANSCODER-HP
    7. 151050
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįĥ亿
    -0.31
    é£İ
    -0.30
    å¼Ģå±ķäºĨ
    -0.28
    å®ĺ宣
    -0.27
     wind
    -0.26
     fl
    -0.26
     overl
    -0.26
    leh
    -0.25
     performed
    -0.25
     limiting
    -0.25
    POSITIVE LOGITS
     QFile
    0.28
     strftime
    0.26
     cref
    0.26
    lijah
    0.26
     Technician
    0.24
     günd
    0.24
     Compression
    0.24
     persön
    0.24
     Complaint
    0.24
     ContentView
    0.24
    Activations Density 0.101%

    No Known Activations