© 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. 42720
    Prev
    Next
    INDEX
    Explanations

    acts of communication

    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
     LoginForm
    -0.26
    érc
    -0.25
     обÑĬ
    -0.25
    oment
    -0.24
    éĻĪè¿°
    -0.24
    coordinate
    -0.24
     remot
    -0.24
    ÑĢеÑģ
    -0.24
    æĥħ
    -0.24
    entai
    -0.23
    POSITIVE LOGITS
     calls
    0.45
     thinks
    0.42
     Calls
    0.34
     notes
    0.31
     think
    0.31
    calls
    0.31
     feels
    0.29
     along
    0.29
     points
    0.29
     replies
    0.29
    Activations Density 0.002%

    No Known Activations