© 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. 27-TRANSCODER-HP
    7. 57696
    Prev
    Next
    INDEX
    Explanations

    species and biodiversity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grade
    -0.27
    поÑĩ
    -0.26
    æıī
    -0.26
     Cit
    -0.26
    uzzle
    -0.26
     Battles
    -0.26
    åįģä¸ĩ
    -0.25
     ring
    -0.25
     grading
    -0.25
    жÑĥ
    -0.24
    POSITIVE LOGITS
     species
    0.52
    çī©ç§į
    0.49
     communities
    0.49
     fauna
    0.48
     flora
    0.47
     biodiversity
    0.45
     community
    0.45
    species
    0.45
     diversity
    0.43
    community
    0.40
    Activations Density 0.021%

    No Known Activations