© 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. 23407
    Prev
    Next
    INDEX
    Explanations

    legal/formal text

    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
    寿
    -0.29
    壽
    -0.26
    عÙĪÙĨ
    -0.26
     sund
    -0.25
    (Set
    -0.24
    (Unit
    -0.24
    оÑı
    -0.24
    åĨ·
    -0.23
    داد
    -0.23
    haul
    -0.23
    POSITIVE LOGITS
    éŃĤ
    0.29
    强æĤį
    0.28
    æ¦Ħ
    0.26
    éľ¹
    0.25
     stage
    0.25
    çĹķ
    0.25
    å§Ķ
    0.24
    ECT
    0.24
    éĶ£
    0.24
    usta
    0.24
    Activations Density 0.002%

    No Known Activations