© 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. 19505
    Prev
    Next
    INDEX
    Explanations

    time periods/cycles

    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
    èĦIJ
    -0.30
    pei
    -0.29
     Pep
    -0.28
    ic
    -0.27
     belie
    -0.27
    ile
    -0.26
    ular
    -0.26
    opor
    -0.26
    ilan
    -0.25
    ystate
    -0.25
    POSITIVE LOGITS
     clouds
    0.32
    arma
    0.29
     times
    0.28
    æķ£
    0.26
     periods
    0.26
    éħ°
    0.26
    两年
    0.26
     Period
    0.26
    ç½Ķ
    0.25
     TIMES
    0.25
    Activations Density 1.047%

    No Known Activations