© 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. 19-TRANSCODER-HP
    7. 6160
    Prev
    Next
    INDEX
    Explanations

    events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.28
     heartbeat
    -0.25
    quisite
    -0.24
    èĥ½è¾¾åĪ°
    -0.23
    quired
    -0.23
     Pound
    -0.23
    roscope
    -0.23
    inea
    -0.23
     reversal
    -0.23
    i
    -0.23
    POSITIVE LOGITS
     suppose
    0.31
    äºĭæĥħ
    0.27
    客
    0.27
    ooled
    0.27
     Suppose
    0.26
    éĤ£ä¹Īç®Ģåįķ
    0.26
    çļĦäºĭæĥħ
    0.26
    ä¸Ģ件äºĭ
    0.25
    çĶ¨éĢĶ
    0.25
    ilon
    0.25
    Activations Density 0.119%

    No Known Activations