© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    events causing reactions

    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
     Appeal
    -0.27
     zwyk
    -0.26
    ripple
    -0.25
    æĬĺ
    -0.25
    razil
    -0.24
    -called
    -0.24
    REFERRED
    -0.24
    éĩĩçĶ¨
    -0.24
    FM
    -0.24
    è·Ĺ
    -0.24
    POSITIVE LOGITS
     sweat
    0.30
    åĶı
    0.29
     breathed
    0.26
    å°ĺ
    0.26
     dust
    0.26
    MediaType
    0.25
    æĤ²åĵĢ
    0.25
     ris
    0.25
     breathing
    0.25
    iasco
    0.25
    Activations Density 0.008%

    No Known Activations