© 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. 39098
    Prev
    Next
    INDEX
    Explanations

    s

    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
    è§ĦèĮĥ
    -0.29
    ecc
    -0.27
    大éģĵ
    -0.26
    orp
    -0.26
    atto
    -0.25
     Cre
    -0.25
    ç»°
    -0.25
    .esp
    -0.24
    è¡¿
    -0.24
    .timedelta
    -0.23
    POSITIVE LOGITS
    utes
    0.27
     ein
    0.26
    象
    0.25
    éĺı
    0.25
    çĨŁ
    0.24
    æĹ¢æĺ¯
    0.24
     human
    0.23
    ologies
    0.23
    lz
    0.23
     Jeb
    0.23
    Activations Density 76.505%

    No Known Activations