© 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. 19107
    Prev
    Next
    INDEX
    Explanations

    albums and songs

    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
    åķĨçĶ¨
    -0.30
    nio
    -0.28
    vez
    -0.27
    nen
    -0.27
    nis
    -0.27
    WO
    -0.26
    æĬ½å¥ĸ
    -0.26
    媾
    -0.26
    SourceType
    -0.26
     heaps
    -0.26
    POSITIVE LOGITS
    ripp
    0.35
    æīĭæĮĩ
    0.28
     Sat
    0.28
    sat
    0.28
    æ³µ
    0.26
    émon
    0.25
    èĵĸ
    0.25
    cake
    0.24
    peria
    0.24
    éĢ»è¾ij
    0.24
    Activations Density 0.044%

    No Known Activations