© 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. 8249
    Prev
    Next
    INDEX
    Explanations

    wind

    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
     amort
    -0.27
    моÑĢ
    -0.26
    loquent
    -0.26
    Protected
    -0.25
    ahan
    -0.25
    ç§į
    -0.24
    åĵĤ
    -0.24
     hand
    -0.24
    ais
    -0.24
    ди
    -0.24
    POSITIVE LOGITS
     velocity
    0.28
    åĮĹæŀģ
    0.28
     poo
    0.27
     tone
    0.26
    èµ·ä¹ī
    0.26
    尺度
    0.25
     HDC
    0.25
    èĸªèµĦ
    0.25
    ä¸Ī夫
    0.25
    éĢŁçİĩ
    0.24
    Activations Density 0.002%

    No Known Activations