© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89319
    Prev
    Next
    INDEX
    Explanations

    replication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    修补
    -0.28
     Californ
    -0.28
    multipart
    -0.26
    çī¹åĪ«å£°æĺİ
    -0.25
    Boom
    -0.24
    ibase
    -0.24
    weigh
    -0.24
    isspace
    -0.24
    Touches
    -0.24
    åıĮèĦļ
    -0.24
    POSITIVE LOGITS
    -connected
    0.28
    éĿŀ常éĩįè¦ģ
    0.28
    HashCode
    0.26
    åĨĻä½ľ
    0.26
    çĽ¸å¹²
    0.25
    tti
    0.24
    å¾Īéĩįè¦ģ
    0.24
    rette
    0.24
    inus
    0.24
    åĨĻçĿĢ
    0.24
    Activations Density 13.174%

    No Known Activations