© 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. 355
    Prev
    Next
    INDEX
    Explanations

    German names/surnames

    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
    ailles
    -0.27
    çī¹æĸ¯
    -0.26
    Fcn
    -0.26
    _SF
    -0.25
    clid
    -0.25
    cratch
    -0.25
    isch
    -0.25
    ius
    -0.25
    esehen
    -0.24
    ä¸īä½į
    -0.23
    POSITIVE LOGITS
    ä½Ī
    0.28
    groupName
    0.27
    é£İéĻ©ç®¡çIJĨ
    0.26
    roups
    0.25
     truth
    0.25
     independent
    0.25
    åĸ§
    0.25
    ä¿¡æģ¯åıijå¸ĥ
    0.24
     independence
    0.24
    runner
    0.24
    Activations Density 0.014%

    No Known Activations