© 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. 23-TRANSCODER-HP
    7. 161880
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķĮ
    -0.31
    æĺ¾
    -0.28
    主åĬ¨
    -0.26
    æİĮæı¡
    -0.26
    ç¡®
    -0.26
    åħį
    -0.26
    åıijå±ķä¸Ń
    -0.26
    (mut
    -0.26
    bound
    -0.26
    çļĦåŃĺåľ¨
    -0.25
    POSITIVE LOGITS
     vår
    0.27
    ÐĴведиÑĤе
    0.26
    eday
    0.25
    PIP
    0.24
     Ðĺменно
    0.24
    unted
    0.23
    æį¯
    0.23
    psilon
    0.23
     mint
    0.23
    _assoc
    0.23
    Activations Density 0.009%

    No Known Activations