© 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. 123610
    Prev
    Next
    INDEX
    Explanations

    unused

    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
    פך
    -0.08
     Kitchen
    -0.07
    不仅仅
    -0.07
    ANDROID
    -0.07
    微量
    -0.07
    มน
    -0.07
     Mortgage
    -0.07
    无私
    -0.07
    ối
    -0.06
     Quite
    -0.06
    POSITIVE LOGITS
    被淘汰
    0.08
     enrol
    0.07
    背叛
    0.07
    .positions
    0.07
     ]↵
    0.07
    ;")↵
    0.07
    申诉
    0.07
    派出
    0.07
    [].
    0.06
     nhiễ
    0.06
    Activations Density 0.005%

    No Known Activations