© 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. 27149
    Prev
    Next
    INDEX
    Explanations

    vulnerability

    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
    此時
    -0.08
    .what
    -0.07
    起到
    -0.07
     NEWS
    -0.07
    -T
    -0.07
    就像
    -0.07
    领导者
    -0.07
    改成
    -0.06
     calm
    -0.06
    展现
    -0.06
    POSITIVE LOGITS
     vulnerabilities
    0.08
    ()));
    0.07
    >';
    0.07
     vulner
    0.07
    >";↵
    0.07
    득
    0.07
    ;
↵
    0.07
    _vertex
    0.07
    >())
    0.07
    廉洁
    0.06
    Activations Density 0.008%

    No Known Activations