© 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. 130017
    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
    èݽ
    -0.28
    å¸ĥ
    -0.27
    漫æŃ¥
    -0.26
    cant
    -0.26
    对她
    -0.26
    å¥¹åľ¨
    -0.26
    æķijåij½
    -0.25
    éļ¾å¾Ĺ
    -0.25
    åijĬè¯ī她
    -0.25
    è·Łå¥¹
    -0.25
    POSITIVE LOGITS
    nen
    0.29
    eneral
    0.27
    éĻ¤éĿŀ
    0.26
    éĻIJ度
    0.25
    uality
    0.25
    _devices
    0.24
    æµIJ
    0.24
    ORITY
    0.24
    çĶ·
    0.24
    zure
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.