© 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. 112090
    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
    åĶ¯ä¸Ģ
    -0.29
    åĶ¯ä¸ĢçļĦ
    -0.26
     search
    -0.26
    urat
    -0.26
    chy
    -0.24
    çķĮçļĦ
    -0.24
    æIJľç´¢
    -0.24
    ç©¿è¡£
    -0.24
    çĥĤ
    -0.23
    jax
    -0.23
    POSITIVE LOGITS
    å²
    0.31
     comps
    0.27
    失è°ĥ
    0.26
    åĬ¨æijĩ
    0.24
    IVES
    0.24
    æ²Ł
    0.23
    è¿Ľä¸ĢæŃ¥
    0.23
    _candidates
    0.23
    aria
    0.22
    æµ°
    0.22
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.