© 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. 30687
    Prev
    Next
    INDEX
    Explanations

    stated

    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
    的年轻人
    -0.07
    الم
    -0.07
    协
    -0.07
    _TH
    -0.06
     allele
    -0.06
    (click
    -0.06
     mentality
    -0.06
     AFP
    -0.06
    副总经理
    -0.06
    /site
    -0.06
    POSITIVE LOGITS
    すで
    0.07
    六年
    0.07
     CharSet
    0.07
     Ves
    0.07
    ˂
    0.07
     constrained
    0.07
    paths
    0.06
     suffering
    0.06
     impeachment
    0.06
     harming
    0.06
    Activations Density 0.003%

    No Known Activations