© 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. 6080
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ä¿İ
    -0.26
     !***
    -0.25
    çĸļ
    -0.24
     snowy
    -0.24
     Intent
    -0.24
     musical
    -0.23
     Musical
    -0.23
    æľ¬åľºæ¯ĶèµĽ
    -0.23
     escort
    -0.23
    çĺ¿
    -0.23
    POSITIVE LOGITS
    è¿ŀ
    0.28
    硬
    0.26
    éĶIJ
    0.26
    posables
    0.24
    äºĨå¤ļå°ij
    0.23
    asan
    0.23
    äºĨä¸Ģéģį
    0.23
    igidBody
    0.23
    odox
    0.22
    жд
    0.22
    Activations Density 0.022%

    No Known Activations