© 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. 96538
    Prev
    Next
    INDEX
    Explanations

    Excerpts from different sources

    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
    èIJĥ
    -0.29
    eci
    -0.28
     mechanically
    -0.28
    uu
    -0.27
     transl
    -0.27
    å°±æľī
    -0.26
    碲
    -0.26
    è¾¾
    -0.26
    otto
    -0.25
     tü
    -0.25
    POSITIVE LOGITS
    -block
    0.31
     arm
    0.27
     russ
    0.26
    block
    0.26
    被æīĵ
    0.26
     ante
    0.26
     costing
    0.26
    åľ°ä¸Ĭ
    0.26
    antan
    0.26
     Arm
    0.25
    Activations Density 0.886%

    No Known Activations