© 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. 5045
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    éľĢè¦ģ
    -0.28
     honeymoon
    -0.26
    æѤ类
    -0.26
    éľĢ
    -0.26
    çĤ¼
    -0.26
    unda
    -0.26
    grade
    -0.25
    umb
    -0.25
     needs
    -0.25
    need
    -0.25
    POSITIVE LOGITS
    esson
    0.32
    eren
    0.28
    个å°ı
    0.25
    å¼ĢéĢļ
    0.25
    å»ĵ
    0.25
    ç¿»å¼Ģ
    0.25
    ({_
    0.24
    è´£ç¼ĸ
    0.24
     Ere
    0.24
    åĮħåĮħ
    0.24
    Activations Density 0.009%

    No Known Activations