© 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. 33-TRANSCODER-HP
    7. 53087
    Prev
    Next
    INDEX
    Explanations

    elections and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èķī
    -0.36
     vic
    -0.31
    atan
    -0.28
     multiplier
    -0.27
    ·æĸ°
    -0.26
     hal
    -0.25
     depressing
    -0.25
    ouble
    -0.24
    æ£ļ
    -0.24
     distraction
    -0.24
    POSITIVE LOGITS
    éľį
    0.26
    inecraft
    0.25
    /el
    0.24
     bedtime
    0.24
    blink
    0.24
    ’int
    0.24
    åĪ°æĿ¥
    0.24
    -country
    0.24
    bow
    0.23
     Charter
    0.23
    Activations Density 0.029%

    No Known Activations