© 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. 128759
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    橑
    -0.07
    [player
    -0.07
    健康产业
    -0.07
    _MATCH
    -0.07
     attravers
    -0.06
    favor
    -0.06
    roscope
    -0.06
    Tick
    -0.06
    有的玩家
    -0.06
    “One
    -0.06
    POSITIVE LOGITS
    餐馆
    0.07
    		 ↵
    0.07
    _mat
    0.07
     gems
    0.07
    שימה
    0.06
     feminine
    0.06
    minimal
    0.06
    -events
    0.06
     increments
    0.06
     classy
    0.06
    Activations Density 0.499%

    No Known Activations