© 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. 111921
    Prev
    Next
    INDEX
    Explanations

    Eastern Europe locations/names

    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
    æľīä¸Ģ次
    -0.28
    anzeigen
    -0.27
    cant
    -0.27
    楫
    -0.26
    uvre
    -0.26
    intr
    -0.25
    ease
    -0.25
    cpt
    -0.25
    åıijè¾¾
    -0.25
     Booth
    -0.25
    POSITIVE LOGITS
    ournals
    0.31
    åIJ«ä¹ī
    0.28
    uliar
    0.28
    驽
    0.27
    than
    0.26
    texts
    0.25
    çĦĺ
    0.25
    centre
    0.24
    miss
    0.24
    马æĭī
    0.23
    Activations Density 0.026%

    No Known Activations