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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8530
    Prev
    Next
    INDEX
    Explanations

    Hall

    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
    人群ä¸Ń
    -0.24
    _subtype
    -0.24
     TestBed
    -0.23
    antaged
    -0.23
    è¿ĺæĥ³
    -0.22
    æijģ
    -0.22
    å°±ç®Ĺæĺ¯
    -0.22
    æĥ³èµ·æĿ¥
    -0.22
    æŁĶæĢ§
    -0.22
    å°±è¿ŀ
    -0.22
    POSITIVE LOGITS
    -seat
    0.29
    ity
    0.28
    åİħ
    0.27
     hand
    0.27
     presence
    0.27
    -room
    0.25
    chair
    0.25
    -night
    0.23
    č↵        č↵
    0.23
    nah
    0.23
    Activations Density 1.981%

    No Known Activations