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. 11-TRANSCODER-HP
    4. 54586
    Prev
    Next
    INDEX
    Explanations

    Alarming/negative tone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç§Ł
    -0.30
    ynes
    -0.29
    éĢī
    -0.29
    (sec
    -0.27
     Syn
    -0.25
    åĬłéĩį
    -0.24
    uma
    -0.24
    orial
    -0.23
     Mate
    -0.23
     sheds
    -0.23
    POSITIVE LOGITS
    åĩĨ
    0.32
    æĥħåĨµè¿Ľè¡Į
    0.27
    uParam
    0.27
    .anim
    0.26
    ä¸Ģè¶Ł
    0.25
    egend
    0.25
    templ
    0.25
    ä¸ľè¥¿
    0.24
    .sl
    0.24
     materials
    0.24
    Activations Density 0.829%

    No Known Activations