© 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. 54336
    Prev
    Next
    INDEX
    Explanations

    French phrases

    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
     av
    -0.34
     em
    -0.34
    æŃ¥
    -0.31
    çĶ¸
    -0.25
     internally
    -0.25
    avra
    -0.25
    bir
    -0.24
    ances
    -0.24
    vir
    -0.24
     alternating
    -0.24
    POSITIVE LOGITS
    _pe
    0.28
    ofil
    0.27
    queeze
    0.26
    eree
    0.26
    uju
    0.26
     Gill
    0.25
     Pe
    0.25
     pe
    0.25
    Pe
    0.24
     Graduate
    0.24
    Activations Density 0.054%

    No Known Activations