© 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. 18300
    Prev
    Next
    INDEX
    Explanations

    measure, measurement

    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
    Īĺ
    -0.27
     shin
    -0.25
    blick
    -0.24
    èĥ±
    -0.24
    pf
    -0.24
    èıģ
    -0.23
    lices
    -0.23
    guid
    -0.23
    xec
    -0.23
    gest
    -0.23
    POSITIVE LOGITS
     measure
    1.28
    æµĭéĩı
    1.21
    measure
    1.15
     Measure
    1.13
     measurement
    1.11
     mesure
    1.11
    æµĭ
    1.11
     measures
    1.09
    Measure
    1.07
     measuring
    1.06
    Activations Density 7.981%

    No Known Activations