© 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. 30-TRANSCODER-HP
    7. 95518
    Prev
    Next
    INDEX
    Explanations

    telecom services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erl
    -0.35
    çĪ±å°Ķåħ°
    -0.29
    æĵ¦
    -0.29
     voice
    -0.29
     BTS
    -0.28
    Sector
    -0.28
     Eb
    -0.27
    Eb
    -0.27
    ìĭľìĬ¤
    -0.26
    ä¿¡
    -0.26
    POSITIVE LOGITS
    entin
    0.28
    .Inf
    0.26
    igm
    0.26
    setId
    0.25
     Wheels
    0.25
    -sidebar
    0.25
     unregister
    0.24
     ($)
    0.24
    çĭ®
    0.24
    -inf
    0.24
    Activations Density 1.158%

    No Known Activations