© 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. 23-TRANSCODER-HP
    7. 24923
    Prev
    Next
    INDEX
    Explanations

    Non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advoc
    -0.29
    agnet
    -0.26
    entai
    -0.26
    çĨĦ
    -0.25
    istrar
    -0.25
    /close
    -0.25
    éĥ½ä¼ļæľī
    -0.25
    íıIJ
    -0.25
    ÂŃt
    -0.24
    REGION
    -0.24
    POSITIVE LOGITS
    ye
    0.25
     Notes
    0.25
    渴
    0.24
     Rather
    0.24
     NOTES
    0.24
    ASA
    0.24
    NSE
    0.24
    èĮĥåĽ´åĨħ
    0.23
    NS
    0.23
     monoc
    0.23
    Activations Density 0.007%

    No Known Activations