© 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. 35-TRANSCODER-HP
    7. 39555
    Prev
    Next
    INDEX
    Explanations

    cities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armor
    -0.32
     boxer
    -0.27
    弩
    -0.27
     colour
    -0.27
     пÑĢидеÑĤÑģÑı
    -0.26
     flavor
    -0.26
    çŃ¹çłģ
    -0.26
     tyre
    -0.25
     armour
    -0.25
    colour
    -0.25
    POSITIVE LOGITS
     Rochester
    0.38
     Atlanta
    0.38
    çĽIJåŁİ
    0.38
     Islamabad
    0.36
     Seattle
    0.36
    è¿ŀäºij港
    0.35
    æĥłå·ŀ
    0.35
     Honolulu
    0.35
     Zambia
    0.35
     Maryland
    0.34
    Activations Density 5.590%

    No Known Activations