© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5132
    Prev
    Next
    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¶
    -0.30
    ulas
    -0.29
    ured
    -0.25
    uye
    -0.25
    èĪĤ
    -0.25
    -lined
    -0.25
    éĢĢ
    -0.24
    olate
    -0.24
    emed
    -0.24
    -lat
    -0.24
    POSITIVE LOGITS
     parity
    0.29
     territory
    0.27
    æ®Ĭ
    0.26
    èijĹ
    0.26
    ãģªãĤĬ
    0.25
     lump
    0.25
     Lump
    0.24
    åĵ²åѦ
    0.24
    ekyll
    0.24
    orton
    0.24
    Activations Density 0.019%

    No Known Activations