© 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. 33-TRANSCODER-HP
    7. 52941
    Prev
    Next
    INDEX
    Explanations

    Locations around the world

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tangent
    -0.27
    AFE
    -0.26
    Fair
    -0.26
    éĺ´å½±
    -0.25
    WER
    -0.25
    ë§ī
    -0.25
    aec
    -0.25
     fair
    -0.25
    amas
    -0.24
    寧
    -0.24
    POSITIVE LOGITS
    åĪĹ
    0.37
    lico
    0.30
    åĮĹè·¯
    0.27
    åĪ©
    0.26
    è·¯
    0.26
     Least
    0.25
    ri
    0.25
    -hot
    0.25
    hot
    0.25
    å®ŀåĬĽ
    0.25
    Activations Density 0.017%

    No Known Activations