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. 3010
    Prev
    Next
    INDEX
    Explanations

    of

    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
    约è°Ī
    -0.29
     hypo
    -0.28
    antt
    -0.27
    æĶ¹èī¯
    -0.26
    ypo
    -0.26
    grim
    -0.25
     infer
    -0.25
     Infer
    -0.25
    mounted
    -0.24
    æĬľ
    -0.24
    POSITIVE LOGITS
    èĦĪ
    0.29
    èĦī
    0.29
     pulses
    0.27
    oplast
    0.27
    NR
    0.26
     Pul
    0.25
    ãĥĹãĥ¬ãĤ¤
    0.25
    åĮ»æ²»
    0.24
     dreaming
    0.24
    rest
    0.23
    Activations Density 0.006%

    No Known Activations