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. 7585
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    DV
    -0.29
     Swinger
    -0.26
    asa
    -0.26
    VRT
    -0.26
    Bat
    -0.26
    Dos
    -0.25
     fps
    -0.25
     hor
    -0.24
    Thing
    -0.24
    dos
    -0.24
    POSITIVE LOGITS
    оÑĩно
    0.25
    è¿Ļæł·åģļ
    0.24
    /null
    0.23
    éĩįåĽŀ
    0.23
    ).(
    0.23
    è¿Ļæł·è¯´
    0.23
    论述
    0.23
    çĬį
    0.23
    such
    0.23
    ç¿»
    0.23
    Activations Density 0.004%

    No Known Activations