© 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. 112264
    Prev
    Next
    INDEX
    Explanations

    # or -

    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
    å¤ı
    -0.29
    ,:,:
    -0.28
    pendicular
    -0.26
    sil
    -0.25
    kir
    -0.25
    ç«¥
    -0.25
    venience
    -0.25
     overd
    -0.25
    hardt
    -0.25
    械
    -0.24
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.28
     ```
    0.28
    说æľį
    0.27
    éĻ°
    0.26
    æĪijæĬĬ
    0.26
    oden
    0.25
     Bedford
    0.25
    åķĨæĬ¥
    0.24
    å§ij
    0.24
    Suc
    0.24
    Activations Density 0.053%

    No Known Activations