© 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. 128696
    Prev
    Next
    INDEX
    Explanations

    greetings

    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
     Denied
    -0.08
    詳しく
    -0.07
     Brittany
    -0.07
     chees
    -0.07
     Somerset
    -0.07
    esta
    -0.07
     oggi
    -0.06
    诗意
    -0.06
    avit
    -0.06
    Fuse
    -0.06
    POSITIVE LOGITS
    قال
    0.07
     turnaround
    0.07
    ℳ
    0.07
    国资委
    0.07
    ⌺
    0.07
     librarian
    0.07
    systems
    0.07
     Juan
    0.07
    轨道
    0.07
    border
    0.07
    Activations Density 0.029%

    No Known Activations