© 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. 123468
    Prev
    Next
    INDEX
    Explanations

    US Court of Appeals documents

    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
    _draft
    -0.08
    打着
    -0.07
    깅
    -0.07
     NRL
    -0.07
     solitary
    -0.06
     fights
    -0.06
    -Co
    -0.06
    ➜
    -0.06
     입장
    -0.06
     secretive
    -0.06
    POSITIVE LOGITS
    ust
    0.07
    ruk
    0.07
     continuar
    0.07
    －
    0.07
     Condition
    0.07
    𫄧
    0.07
    uania
    0.07
     instal
    0.06
    מקד
    0.06
    켤
    0.06
    Activations Density 0.003%

    No Known Activations