© 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. 96380
    Prev
    Next
    INDEX
    Explanations

    plant disease, pest control

    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
    }//
    -0.30
     defaultProps
    -0.28
    纡
    -0.28
    å¹¹
    -0.28
     exited
    -0.28
    åĪ¶åº¦æĶ¹éĿ©
    -0.27
    è¿IJæ°Ķ
    -0.25
    zac
    -0.25
     enter
    -0.24
    éĢĢ
    -0.23
    POSITIVE LOGITS
    xad
    0.26
    Rod
    0.25
    è£Ļ
    0.25
    éŨ
    0.25
    OAD
    0.25
    åĴ¬
    0.25
    rod
    0.25
    lien
    0.24
    è·³
    0.24
    pline
    0.24
    Activations Density 0.883%

    No Known Activations