© 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. 4841
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Pioneer
    -0.26
    满åĪĨ
    -0.25
    Ke
    -0.24
     Mayo
    -0.24
    uien
    -0.24
     Mach
    -0.23
    hy
    -0.23
     Fraud
    -0.23
     Joseph
    -0.23
     keep
    -0.23
    POSITIVE LOGITS
    çĭ¬
    0.27
    ìŀĦ
    0.26
    ŀĭ
    0.25
    "))))↵
    0.25
     HOR
    0.25
    ĥĿ
    0.24
    ?")↵
    0.24
    çĥ©
    0.24
    _DP
    0.24
    åķ
    0.24
    Activations Density 0.373%

    No Known Activations