© 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. 206
    Prev
    Next
    INDEX
    Explanations

    corps

    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
    åħ¬ä¼Ĺ
    -0.25
    Het
    -0.25
    //}↵
    -0.24
    áfico
    -0.24
    çĦ¦çĤ¹
    -0.24
    &)↵
    -0.23
    ernes
    -0.23
    æĶ¿
    -0.23
    amura
    -0.23
    çĪĨçĤ¸
    -0.23
    POSITIVE LOGITS
     internals
    0.27
    éģĩä¸Ĭ
    0.26
     Washer
    0.25
    als
    0.25
    nob
    0.24
     maj
    0.24
    æ¯ıå½ĵ
    0.24
     rev
    0.24
    SpaceItem
    0.24
    IQ
    0.23
    Activations Density 0.058%

    No Known Activations