© 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. 39028
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    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
    æĢİä¹Īä¼ļ
    -0.20
     ner
    -0.19
     doomed
    -0.19
     hut
    -0.18
     dealt
    -0.18
     fearing
    -0.17
    ä¼ļè§īå¾Ĺ
    -0.17
    åıĺå¾ĹæĽ´
    -0.17
     nit
    -0.17
     punishing
    -0.17
    POSITIVE LOGITS
    2
    0.29
    3
    0.28
    5
    0.27
    7
    0.27
    4
    0.27
    6
    0.26
    8
    0.25
    9
    0.25
    1
    0.25
    0
    0.25
    Activations Density 56.506%

    No Known Activations