© 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. 39709
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    ç±»
    -0.30
    åı¯èĥ½
    -0.27
    礼
    -0.26
    .$
    -0.25
    æĽ¾ç»ı
    -0.24
     (?
    -0.24
     chÃŃnh
    -0.24
    -0.24
    èĥ½å¤Ł
    -0.24
    å·²ç»ı
    -0.24
    POSITIVE LOGITS
    aura
    0.33
    agrams
    0.32
    duc
    0.32
    artz
    0.31
    dated
    0.30
    tica
    0.29
    aur
    0.29
    æ°ĺ
    0.29
    hid
    0.29
    aab
    0.28
    Activations Density 0.079%

    No Known Activations