© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162071
    Prev
    Next
    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Speaker
    -0.27
    ongs
    -0.27
     Speaker
    -0.26
    coe
    -0.25
    ainment
    -0.25
    ocking
    -0.24
    产åĵģçłĶåıij
    -0.24
    ight
    -0.24
    hip
    -0.24
    ç»ĦåĽ¾
    -0.24
    POSITIVE LOGITS
    lesen
    0.31
    çķĻåѦçĶŁ
    0.27
     realm
    0.26
    sist
    0.24
     grading
    0.24
    ä¸Ńæĸ°ç½ij
    0.23
    _chan
    0.23
    itime
    0.23
    dle
    0.23
    è¾ĺ
    0.23
    Activations Density 0.010%

    No Known Activations