© 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. 64237
    Prev
    Next
    INDEX
    Explanations

    scientific/technical contexts

    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
     ahead
    -0.31
    åīįåĪĹ
    -0.30
    ahead
    -0.28
    ogr
    -0.26
     identities
    -0.25
    antry
    -0.24
     identity
    -0.24
    油价
    -0.24
    Else
    -0.24
    ony
    -0.24
    POSITIVE LOGITS
    aurus
    0.31
    ivo
    0.29
    ERENCE
    0.28
    /topics
    0.28
    oire
    0.28
    éĢģåİ»
    0.27
    .MockMvc
    0.25
    ervative
    0.24
    é»ij马
    0.24
                        ↵                    ↵
    0.24
    Activations Density 16.010%

    No Known Activations