Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 10819
    Prev
    Next
    INDEX
    Explanations

    array, sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inces
    -0.07
    �
    -0.07
    彷
    -0.07
     Mack
    -0.06
     amongst
    -0.06
     shook
    -0.06
     coded
    -0.06
     Contents
    -0.06
    歳
    -0.06
     palabras
    -0.06
    POSITIVE LOGITS
    /buttons
    0.08
     commuting
    0.07
     proofs
    0.07
    MaxLength
    0.07
    蝼
    0.07
     الاقتصادية
    0.07
    半导
    0.07
    قار
    0.07
    Yeah
    0.07
    救治
    0.07
    Activations Density 0.012%

    No Known Activations