© 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. 22-TRANSCODER-HP
    7. 87820
    Prev
    Next
    INDEX
    Explanations

    Code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icing
    -0.30
    opup
    -0.26
    -dashboard
    -0.26
    isks
    -0.25
    -token
    -0.25
     hem
    -0.25
    åı°
    -0.25
    -budget
    -0.25
    tier
    -0.24
    ãĢģ“
    -0.24
    POSITIVE LOGITS
    http
    0.29
     beyond
    0.29
     further
    0.26
     pd
    0.26
    转载请
    0.26
     далÑĮÑĪе
    0.25
     http
    0.25
     past
    0.24
    Further
    0.24
    è®°
    0.24
    Activations Density 0.033%

    No Known Activations