© 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. 32-TRANSCODER-HP
    7. 42246
    Prev
    Next
    INDEX
    Explanations

    esar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mo
    -0.33
     positives
    -0.31
    tap
    -0.30
    mo
    -0.28
     mole
    -0.27
     pan
    -0.27
    éĶ£
    -0.26
    lec
    -0.26
    mol
    -0.26
     Colon
    -0.25
    POSITIVE LOGITS
    声
    0.29
    èģ²
    0.28
    esar
    0.27
     Arch
    0.27
    å¡ŀå°Ķ
    0.27
    åľ°çĤ¹
    0.26
    daemon
    0.25
    æł¸å¿ĥåĮº
    0.24
    Pont
    0.24
    .breakpoints
    0.24
    Activations Density 0.001%

    No Known Activations