© 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. 87193
    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
    顺便
    -0.26
     Newton
    -0.26
    个å°ıæŶ
    -0.25
    ç´¯äºĨ
    -0.25
    å®Įç¾İçļĦ
    -0.25
     endorse
    -0.25
    ENA
    -0.24
    Newton
    -0.24
    uth
    -0.24
    á»ĩt
    -0.24
    POSITIVE LOGITS
     Unblock
    0.26
    union
    0.26
    SENS
    0.25
    tie
    0.25
    æĭīå¼Ģ
    0.25
    åĽĽå¤Ħ
    0.25
    TURN
    0.24
    èĩªèIJ¥
    0.24
    éĩĩ
    0.24
    å¤Ħå¤Ħ
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.