© 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. 42594
    Prev
    Next
    INDEX
    Explanations

    3

    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
    响
    -0.07
     susceptible
    -0.07
    atisfaction
    -0.07
    メディア
    -0.07
    VERSION
    -0.07
    �
    -0.07
    MET
    -0.07
     appreciation
    -0.07
     respectful
    -0.07
    听话
    -0.07
    POSITIVE LOGITS
    력을
    0.07
    !/
    0.07
    //*[
    0.06
    填
    0.06
     Atl
    0.06
    aina
    0.06
    	↵	↵	↵
    0.06
    ++){
↵
    0.06
     british
    0.06
     Yam
    0.06
    Activations Density 0.001%

    No Known Activations