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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 1117
    Prev
    Next
    INDEX
    Explanations

    preference

    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
     Satoshi
    -0.07
     antioxidant
    -0.07
     journée
    -0.07
    структор
    -0.07
    _tri
    -0.07
    .ne
    -0.07
     돌
    -0.07
    .onNext
    -0.07
     bigger
    -0.07
    ネ
    -0.07
    POSITIVE LOGITS
     preferences
    0.08
    㬮
    0.08
    -hearted
    0.07
    ﻀ
    0.07
    preferences
    0.07
    低保
    0.07
    这部分
    0.07
    因为他们
    0.07
    Window
    0.07
    Unsafe
    0.07
    Activations Density 0.010%

    No Known Activations