Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 3127
    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
     safety
    -0.28
    å¤įæ´»
    -0.27
    è¿ĺæľīå¾Īå¤ļ
    -0.26
    alez
    -0.26
    alen
    -0.26
    æ¯Ķ
    -0.25
    à¸ģระà¸Ī
    -0.25
    åİŁæłĩé¢ĺ
    -0.25
    è¶ħè¿ĩ
    -0.25
    èĩ³äºİ
    -0.25
    POSITIVE LOGITS
    è¿Ļ个人
    0.28
    ¦
    0.27
     Tactics
    0.24
    leshoot
    0.24
     bindActionCreators
    0.24
    toJson
    0.24
    å¾Ĺä½ı
    0.24
    .characters
    0.24
    pository
    0.24
     interceptor
    0.24
    Activations Density 0.001%

    No Known Activations