© 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. 31-TRANSCODER-HP
    7. 19238
    Prev
    Next
    INDEX
    Explanations

    base

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EGA
    -0.31
    หาย
    -0.26
     Fin
    -0.26
    èĢģ大
    -0.24
    inus
    -0.24
    Lost
    -0.24
    åĭŁ
    -0.24
    gages
    -0.23
    åŃ©
    -0.23
     om
    -0.23
    POSITIVE LOGITS
     base
    0.77
    base
    0.66
     sides
    0.62
     Base
    0.61
    .base
    0.60
    Base
    0.59
    _base
    0.58
     bases
    0.57
    -base
    0.55
    	base
    0.55
    Activations Density 17.701%

    No Known Activations