© 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. 54230
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    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
    æĬ½è±¡
    -0.33
    dr
    -0.27
    á»ĵn
    -0.27
     dr
    -0.26
    åĽ½å®¶
    -0.26
     han
    -0.26
    drs
    -0.25
    ite
    -0.25
    æ±ī
    -0.25
     abstract
    -0.25
    POSITIVE LOGITS
    ke
    0.31
    -phase
    0.30
    oker
    0.27
    ephy
    0.26
    ök
    0.26
     каÑĩ
    0.25
     tunes
    0.25
     phase
    0.25
    误
    0.25
    ISC
    0.25
    Activations Density 0.202%

    No Known Activations