© 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. 57214
    Prev
    Next
    INDEX
    Explanations

    Source code

    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
    æ¦Ĥ念
    -0.39
     conceptual
    -0.38
     concepts
    -0.36
    concept
    -0.36
     concept
    -0.34
     Concept
    -0.34
     Concepts
    -0.34
     subdivision
    -0.32
     abstract
    -0.32
    Concept
    -0.32
    POSITIVE LOGITS
    çŀ»
    0.28
    loom
    0.27
    rott
    0.26
    ichert
    0.26
    è¾ĵ
    0.25
     sliders
    0.25
     Prim
    0.25
    ington
    0.24
     slide
    0.24
    .peek
    0.24
    Activations Density 0.008%

    No Known Activations