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. 27-TRANSCODER-HP
    4. 685
    Prev
    Next
    INDEX
    Explanations

    code and data analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åΰä½į
    -0.26
     matrix
    -0.26
     motor
    -0.26
    ices
    -0.25
     as
    -0.25
    atars
    -0.25
    INGTON
    -0.25
    å°½åı¯èĥ½
    -0.25
     Bounty
    -0.25
    è£ħ
    -0.24
    POSITIVE LOGITS
    ApiController
    0.31
    TextStyle
    0.28
     OnTrigger
    0.26
    llx
    0.25
    aque
    0.25
    æ·¼
    0.25
    borough
    0.24
     automáticamente
    0.24
     meis
    0.24
    VALUES
    0.23
    Activations Density 0.002%

    No Known Activations