© 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. 27-TRANSCODER-HP
    7. 56930
    Prev
    Next
    INDEX
    Explanations

    code or URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nano
    -0.26
     solo
    -0.25
    esto
    -0.24
     conver
    -0.23
    纳米
    -0.23
    E
    -0.23
     appearing
    -0.23
    è·¨è¶Ĭå¼ı
    -0.23
     Auto
    -0.23
     erg
    -0.23
    POSITIVE LOGITS
    缸åıį
    0.32
    éĢ»
    0.27
    æĭĽåij¼
    0.26
    glas
    0.26
    giene
    0.26
    管çIJĨå·¥ä½ľ
    0.25
    éŁ³åĵį
    0.25
    ева
    0.24
    尺度
    0.24
    agnet
    0.24
    Activations Density 0.002%

    No Known Activations