© 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. 22-TRANSCODER-HP
    7. 129963
    Prev
    Next
    INDEX
    Explanations

    Instructions, advice, technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıįè¿ĩæĿ¥
    -0.29
    æį
    -0.28
    å¾Ĺèµ·
    -0.27
    tracts
    -0.27
    uur
    -0.26
     baÅŁÄ±nda
    -0.26
     overthrow
    -0.25
    pector
    -0.25
    å¢ī
    -0.25
    æį¢ä¸ª
    -0.25
    POSITIVE LOGITS
    çĭĹ
    0.29
    ing
    0.29
    ino
    0.28
    åĸľ
    0.27
     Rh
    0.26
    ask
    0.26
     Barrier
    0.26
    窦
    0.25
    RC
    0.25
    ros
    0.25
    Activations Density 0.002%

    No Known Activations