© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23956
    Prev
    Next
    INDEX
    Explanations

    Webpage snippets

    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
    rsa
    -0.27
    leans
    -0.25
    icensed
    -0.25
    广åijĬæľįåĬ¡
    -0.24
    ]("
    -0.24
    缩
    -0.24
    éķľ
    -0.24
    (Method
    -0.24
     prevState
    -0.24
     Soccer
    -0.24
    POSITIVE LOGITS
    串
    0.28
    emy
    0.27
    æį·
    0.27
     haul
    0.26
    sheets
    0.26
    çĤĬ
    0.25
    路线
    0.25
    acy
    0.25
    ential
    0.25
     hauling
    0.24
    Activations Density 0.000%

    No Known Activations