© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 2960
    Prev
    Next
    INDEX
    Explanations

    legal statutes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	synchronized
    -0.07
    isses
    -0.07
    -lnd
    -0.07
    achen
    -0.07
    씻
    -0.07
    实惠
    -0.07
    镄
    -0.07
    -s
    -0.07
    坼
    -0.06
    专
    -0.06
    POSITIVE LOGITS
     MODE
    0.07
     bal
    0.07
     głównie
    0.07
    (INT
    0.06
    CLUDING
    0.06
     stat
    0.06
    뭬
    0.06
     admir
    0.06
     قال
    0.06
    SENT
    0.06
    Activations Density 0.035%

    No Known Activations