© 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. 4-TRANSCODER-HP
    7. 74
    Prev
    Next
    INDEX
    Explanations

    online discussions/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Circ
    -0.25
     вÑĭб
    -0.25
    ÑĻ
    -0.24
    ãĥľãĥ¼ãĥī
    -0.24
    æijĦå½±å¸Ī
    -0.24
     torture
    -0.24
     reserv
    -0.23
    Verb
    -0.23
    ont
    -0.23
    ience
    -0.23
    POSITIVE LOGITS
    åĿ¡
    0.30
    åĽ½ç±į
    0.28
    -fw
    0.27
    hardt
    0.26
    InitialState
    0.25
    ProcessEvent
    0.25
    ä¸ŃåĽ½å¸Ĥåľº
    0.25
    çĶ¨æīĭ
    0.24
    éal
    0.24
    parer
    0.24
    Activations Density 0.052%

    No Known Activations