© 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. 4952
    Prev
    Next
    INDEX
    Explanations

    public

    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
    oust
    -0.28
    åIJĮäºĭ
    -0.23
    ¬
    -0.23
    äºĴåĪ©
    -0.23
     contributes
    -0.23
     Decl
    -0.23
    åĩºåħ¥
    -0.23
    ÑįÑĤ
    -0.23
    éĶ¯
    -0.23
     retract
    -0.23
    POSITIVE LOGITS
     Trio
    0.28
    *)_
    0.26
    peror
    0.25
    ogany
    0.24
    ","\
    0.23
     fresh
    0.23
    getApplication
    0.23
    糸
    0.23
     Connectivity
    0.23
    ceries
    0.23
    Activations Density 0.003%

    No Known Activations