© 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. 43848
    Prev
    Next
    INDEX
    Explanations

    Medical/Technical documentation

    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
    proj
    -0.26
    nez
    -0.26
     nicely
    -0.25
     act
    -0.25
    éĢ¾
    -0.25
    以为
    -0.25
    åĨ²
    -0.24
     proj
    -0.24
     Translation
    -0.24
     Sold
    -0.24
    POSITIVE LOGITS
    çĥŃ
    0.34
    als
    0.30
    åıijçĥŃ
    0.29
     fever
    0.29
    çĨ±
    0.29
    entifier
    0.29
    _hot
    0.28
    fare
    0.28
    al
    0.27
     Fever
    0.27
    Activations Density 0.000%

    No Known Activations