© 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. 32-TRANSCODER-HP
    7. 42244
    Prev
    Next
    INDEX
    Explanations

    Code, licenses, European references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WE
    -0.24
    令
    -0.24
    alen
    -0.24
     drain
    -0.24
    True
    -0.24
    owe
    -0.23
    mist
    -0.23
    åĢĵ
    -0.23
    kad
    -0.23
    KE
    -0.23
    POSITIVE LOGITS
    Aus
    0.28
    αι
    0.28
    etails
    0.27
    è§Ĩ
    0.27
    овоÑĢ
    0.26
    åĢĶ
    0.26
    éĺī
    0.23
     License
    0.23
    tra
    0.23
    sonian
    0.23
    Activations Density 0.012%

    No Known Activations