© 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. 130426
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    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
     unloaded
    -0.28
    toDate
    -0.28
    .loadData
    -0.28
    loading
    -0.27
    çĪµ
    -0.25
    Injected
    -0.25
    anni
    -0.24
    /classes
    -0.24
    ÅĽni
    -0.24
    åıijèµ·
    -0.23
    POSITIVE LOGITS
    asan
    0.27
    ugs
    0.26
    emas
    0.26
    æķ¦
    0.26
    æ®Ĭ
    0.26
    åĩłæŃ¥
    0.26
    åħµé©¬
    0.25
    .only
    0.25
    enta
    0.24
    UME
    0.24
    Activations Density 2.168%

    No Known Activations