© 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. 12-TRANSCODER-HP
    7. 22505
    Prev
    Next
    INDEX
    Explanations

    Benedict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conversion
    -0.26
     flip
    -0.25
    çĶ¨è½¦
    -0.25
     fiat
    -0.25
    .Binary
    -0.24
    ëªħ
    -0.24
     boxing
    -0.24
    身价
    -0.24
    bubble
    -0.24
     Vince
    -0.24
    POSITIVE LOGITS
     tro
    0.26
     offerings
    0.26
    buie
    0.25
    china
    0.25
    触
    0.25
     tast
    0.24
    sciously
    0.24
    _SLEEP
    0.24
     dr
    0.24
    entially
    0.23
    Activations Density 0.000%

    No Known Activations