© 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. 378
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    æİĴæŁ¥
    -0.28
    æ½ŀ
    -0.26
     legion
    -0.26
    å½ĵåīįä½įç½®
    -0.23
    *n
    -0.23
    å½ĵãģ¦
    -0.23
     pris
    -0.23
    acons
    -0.23
     blocking
    -0.23
    ux
    -0.23
    POSITIVE LOGITS
    axe
    0.31
    å¤©çľŁ
    0.31
    eder
    0.26
    -Se
    0.26
    CED
    0.25
    CSR
    0.24
    ivet
    0.24
     scen
    0.24
    APH
    0.24
    èĩ´
    0.24
    Activations Density 0.040%

    No Known Activations