© 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. 87907
    Prev
    Next
    INDEX
    Explanations

    Superlatives

    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
     Ay
    -0.28
    arus
    -0.27
     distinguished
    -0.27
     key
    -0.26
    ä¸ŃæľĢ
    -0.25
    æľĢ容æĺĵ
    -0.25
    å¤į
    -0.24
    ay
    -0.24
     prime
    -0.24
    æķħ
    -0.24
    POSITIVE LOGITS
    ħ§
    0.27
     Tate
    0.26
    еб
    0.24
    åĪ¶åº¦æĶ¹éĿ©
    0.24
    iverse
    0.24
    缸åħ³ä¿¡æģ¯
    0.24
    еÑĤе
    0.24
    markt
    0.24
    ITH
    0.23
    eba
    0.23
    Activations Density 0.010%

    No Known Activations