© 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. 20-TRANSCODER-HP
    7. 130468
    Prev
    Next
    INDEX
    Explanations

    Content revision/editing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķĻ
    -0.26
    åı¯è¡Į
    -0.26
    RETURN
    -0.25
     avail
    -0.25
    avad
    -0.25
    ä¸įå¦Ĥ
    -0.25
    夫
    -0.24
    çķı
    -0.23
     Comparable
    -0.23
    felt
    -0.23
    POSITIVE LOGITS
    çģŀ
    0.27
    omaly
    0.26
     terms
    0.25
    ç§ĥ
    0.25
    襲
    0.25
    oster
    0.25
     sting
    0.24
    oste
    0.24
    arp
    0.24
    terms
    0.24
    Activations Density 0.686%

    No Known Activations