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. 7-TRANSCODER-HP
    4. 24120
    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_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¢ģ
    -0.26
     Trailer
    -0.25
    ACTIVE
    -0.25
    elta
    -0.25
    ÑĮ
    -0.25
    ãĤ
    -0.24
    éŀħ
    -0.24
    implemented
    -0.24
    imator
    -0.24
     vill
    -0.24
    POSITIVE LOGITS
    inus
    0.28
    [--
    0.26
     ride
    0.26
    anic
    0.25
     coaster
    0.25
    cdc
    0.25
     colspan
    0.25
    èµĽåĮº
    0.25
    çľĭå¾ħ
    0.24
    istic
    0.24
    Activations Density 0.001%

    No Known Activations