© 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. 9084
    Prev
    Next
    INDEX
    Explanations

    extracted text

    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
    mbH
    -0.27
    uries
    -0.26
     fy
    -0.26
    ADX
    -0.25
    .fx
    -0.24
    ensen
    -0.24
    obra
    -0.23
    asons
    -0.23
    åĽ½äºº
    -0.23
     Roland
    -0.23
    POSITIVE LOGITS
     Unlock
    0.40
    åį¸
    0.39
     unlock
    0.39
    解æĶ¾
    0.38
    å¼ĢæĶ¾
    0.38
    å¼ĢæºIJ
    0.38
    æĶ¾å¼Ģ
    0.38
    unlock
    0.38
    解éĻ¤
    0.38
    æķŀå¼Ģ
    0.37
    Activations Density 0.000%

    No Known Activations