© 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. 30-TRANSCODER-HP
    7. 96726
    Prev
    Next
    INDEX
    Explanations

    combining different things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucken
    -0.26
     sent
    -0.26
     Ga
    -0.26
    æģ¤
    -0.25
    Defs
    -0.25
    ãĤ¹ãĤ¿ãĥ¼
    -0.24
    Kevin
    -0.24
     Sent
    -0.24
     instructional
    -0.24
    SCAN
    -0.23
    POSITIVE LOGITS
     vess
    0.28
    侧
    0.27
    asse
    0.27
    çĿĢçľ¼
    0.27
    .mods
    0.27
    bled
    0.27
    bling
    0.26
    -bin
    0.26
    ëĦ¤
    0.26
    ç®±
    0.25
    Activations Density 0.006%

    No Known Activations