© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5716
    Prev
    Next
    INDEX
    Explanations

    progressive diseases

    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
    æĹ©
    -0.26
     magna
    -0.26
    æĥĬ
    -0.25
    ä»ħ
    -0.25
    èģĬ
    -0.24
    é¢ĦçķĻ
    -0.24
    åŁºæķ°
    -0.24
     consent
    -0.24
    以èĩ³äºİ
    -0.24
    æĹ¶æľº
    -0.23
    POSITIVE LOGITS
    ativity
    0.27
     rev
    0.26
    éĴ±è´¢
    0.25
    æīĢæīĢ
    0.24
     Bounty
    0.24
    ellation
    0.23
    tractor
    0.23
    дол
    0.23
    çİĩ为
    0.23
    æĥ³è±¡åĬĽ
    0.23
    Activations Density 0.015%

    No Known Activations