© 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. 6447
    Prev
    Next
    INDEX
    Explanations

    example

    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
     curs
    -0.30
    就好
    -0.29
    ÂŃs
    -0.28
    ÂŃi
    -0.26
    intl
    -0.25
    CHAN
    -0.25
    esen
    -0.25
    eson
    -0.24
    èģ±
    -0.24
    esch
    -0.24
    POSITIVE LOGITS
    otte
    0.31
    诸
    0.28
    Nested
    0.25
    åĩºçĤī
    0.25
    ä¹³
    0.25
    Both
    0.24
    (side
    0.24
    å±Ĥåĩºä¸įç©·
    0.24
    otive
    0.24
    ãĥŀãĥ³
    0.23
    Activations Density 0.043%

    No Known Activations