© 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. 53310
    Prev
    Next
    INDEX
    Explanations

    personal experiences and opinions

    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
    hog
    -0.30
    hä
    -0.29
    çİ°
    -0.26
    hon
    -0.25
     SEND
    -0.25
    vae
    -0.25
     undone
    -0.24
    æĬµå¾¡
    -0.24
     acknowledgement
    -0.23
     unh
    -0.23
    POSITIVE LOGITS
    OLA
    0.26
     Care
    0.26
    omatic
    0.25
    olo
    0.25
     care
    0.25
    ulum
    0.24
    å°±æĺ¯è¦ģ
    0.24
    ivers
    0.24
     Potter
    0.24
    声éģĵ
    0.24
    Activations Density 0.021%

    No Known Activations