© 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. 87700
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åIJĦå¼Ĥ
    -0.28
    iven
    -0.27
    esthesia
    -0.26
    ç¯Ħ
    -0.25
    åį´è¢«
    -0.25
     обÑıз
    -0.24
     scand
    -0.24
    æĽĿåħī
    -0.24
    åĽ¿
    -0.24
     varied
    -0.23
    POSITIVE LOGITS
     recru
    0.26
    娣
    0.25
    å³Ń
    0.25
    chap
    0.24
     Crack
    0.24
    quete
    0.24
    çľģå§Ķ
    0.24
    RAIN
    0.24
            č↵
    0.24
    å¹²äºĭ
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.