© 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. 111258
    Prev
    Next
    INDEX
    Explanations

    orian

    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
    葡萄
    -0.08
    审理
    -0.08
    اث
    -0.07
    shake
    -0.07
     Multiple
    -0.07
     women
    -0.07
    斑
    -0.07
    iddleware
    -0.06
    曲线
    -0.06
     streak
    -0.06
    POSITIVE LOGITS
     mộ
    0.08
    Old
    0.07
     получи
    0.07
     modèle
    0.07
     HTC
    0.07
     Leo
    0.07
     importing
    0.07
     portrays
    0.06
     terrified
    0.06
     Voyager
    0.06
    Activations Density 0.004%

    No Known Activations