© 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. 8477
    Prev
    Next
    INDEX
    Explanations

    Area measurements

    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
    çĶŁæ´»çݯå¢ĥ
    -0.28
    çªģ
    -0.27
    óst
    -0.26
    á»ķi
    -0.26
    硬件
    -0.26
    çĶļä¹Ī
    -0.25
    å¹²ä»Ģä¹Ī
    -0.25
    软
    -0.25
     burning
    -0.25
    singular
    -0.24
    POSITIVE LOGITS
    acular
    0.27
    ä½ĵ积
    0.26
     volumes
    0.25
    缴å¾Ħ
    0.25
     lengths
    0.25
     approach
    0.25
    .vm
    0.25
    尺度
    0.24
     volume
    0.24
     radius
    0.24
    Activations Density 0.008%

    No Known Activations