© 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. 23593
    Prev
    Next
    INDEX
    Explanations

    formal contexts

    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
    -reader
    -0.27
    cip
    -0.27
     metav
    -0.25
    课
    -0.25
    etail
    -0.25
     viet
    -0.24
    .presentation
    -0.24
    jin
    -0.24
    _]
    -0.24
    æŃ¹
    -0.24
    POSITIVE LOGITS
    çįĴ
    0.29
     shave
    0.29
    梢
    0.25
    头åıij
    0.25
    æīŃ转
    0.24
     slash
    0.24
    åıijå±ķæĸ¹åIJij
    0.24
    Oi
    0.24
     scream
    0.23
     Majesty
    0.23
    Activations Density 0.000%

    No Known Activations