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. 15021
    Prev
    Next
    INDEX
    Explanations

    Most

    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
    çĩİ
    -0.27
     vant
    -0.26
    缮
    -0.26
    uale
    -0.26
     superclass
    -0.26
     Dra
    -0.26
     fortunately
    -0.26
    éļĹ
    -0.25
     afore
    -0.25
    ToBounds
    -0.25
    POSITIVE LOGITS
    annon
    0.25
    éĻį
    0.24
    è©Ī
    0.24
    íĻĺ
    0.23
     amen
    0.23
    âĺħâĺħ
    0.23
    æ¸ħé¦Ļ
    0.23
    inski
    0.23
     traces
    0.23
    preh
    0.23
    Activations Density 0.004%

    No Known Activations