© 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. 111875
    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
    ournals
    -0.25
    oday
    -0.25
    è¶³å¤Ł
    -0.24
    æľºåĬ¨
    -0.23
    幸
    -0.23
    ssi
    -0.23
    å¹²
    -0.23
    è¸Ĭ
    -0.23
    ki
    -0.23
    ä¼İ
    -0.23
    POSITIVE LOGITS
    ãĥľãĥ¼ãĥī
    0.29
    äºĶè¡Į
    0.28
     peg
    0.26
     Peg
    0.24
    Cpp
    0.24
    ãģĿãĤĮãģ«
    0.24
    }}"↵
    0.23
    ugu
    0.23
    -pound
    0.22
    åĩĢèµĦ产
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.