© 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. 12-TRANSCODER-HP
    7. 23270
    Prev
    Next
    INDEX
    Explanations

    code, articles, legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çİ°å®ŀ
    -0.26
    hint
    -0.26
    >>>(
    -0.25
     RVA
    -0.25
    票
    -0.25
    峦
    -0.24
     STATS
    -0.24
    jspx
    -0.24
    åı·çº¿
    -0.24
     quelque
    -0.24
    POSITIVE LOGITS
    Kit
    0.29
    满
    0.28
    满äºĨ
    0.27
    _iso
    0.27
    reet
    0.26
    enses
    0.25
    滿
    0.25
     kit
    0.25
    iores
    0.24
    æīĵæī°
    0.24
    Activations Density 0.002%

    No Known Activations