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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98519
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bum
    -0.27
    alis
    -0.26
    ery
    -0.26
    åĵģæł¼
    -0.23
    è½®
    -0.23
    éĥ¨ä¸»ä»»
    -0.23
    æľµ
    -0.23
    é¹Ĭ
    -0.23
    çIJ¼
    -0.23
     regarding
    -0.22
    POSITIVE LOGITS
     resign
    0.25
    =start
    0.25
    Become
    0.24
     franca
    0.24
     SKF
    0.24
    @$
    0.24
    èĦĨå¼±
    0.23
     Westminster
    0.23
    @m
    0.23
    [Unit
    0.22
    Activations Density 0.140%

    No Known Activations