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. 15320
    Prev
    Next
    INDEX
    Explanations

    URLs and licenses

    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
    ä»ĸåıĪ
    -0.27
    ARA
    -0.27
    engan
    -0.25
    éĴ¤
    -0.25
    /AFP
    -0.24
    ngen
    -0.24
    éĿ¢ç§¯çº¦
    -0.24
     hindi
    -0.24
    ihn
    -0.24
    ÑģÑĤÑĥп
    -0.24
    POSITIVE LOGITS
     https
    0.81
     http
    0.79
    https
    0.71
    http
    0.70
    :http
    0.60
    (http
    0.57
    	http
    0.56
    -http
    0.48
     here
    0.45
    .http
    0.44
    Activations Density 0.139%

    No Known Activations