Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 128059
    Prev
    Next
    INDEX
    Explanations

    Rs

    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
    _fixture
    -0.07
    新冠
    -0.07
     matchup
    -0.07
    ATH
    -0.07
    QS
    -0.07
    ={"/
    -0.07
    入境
    -0.07
    xef
    -0.07
    fortunate
    -0.07
    (dep
    -0.07
    POSITIVE LOGITS
     brute
    0.08
    推崇
    0.07
     Rs
    0.07
    低廉
    0.07
    笔者
    0.07
    サイズ
    0.07
     administering
    0.07
    -authored
    0.06
    邮寄
    0.06
    她们
    0.06
    Activations Density 0.003%

    No Known Activations