© 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. 96249
    Prev
    Next
    INDEX
    Explanations

    spider

    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
     hal
    -0.28
    unker
    -0.27
    tank
    -0.26
    æµij
    -0.26
    _alias
    -0.26
    èĪ«
    -0.25
    unk
    -0.25
     Pike
    -0.25
     flank
    -0.25
    hält
    -0.24
    POSITIVE LOGITS
    èľĺèĽĽ
    0.47
     spider
    0.41
    çĪ¬
    0.40
     spiders
    0.39
    Spider
    0.38
    ç»ĩ
    0.38
    èĽĽ
    0.34
    纺ç»ĩ
    0.34
    纺
    0.33
     threads
    0.32
    Activations Density 0.009%

    No Known Activations