© 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. 48561
    Prev
    Next
    INDEX
    Explanations

    deficiency

    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
     conducive
    -0.07
     dõi
    -0.07
    clear
    -0.07
    認め
    -0.07
    _Menu
    -0.07
    ɯ
    -0.07
    	sound
    -0.07
    وظ
    -0.07
     polite
    -0.07
    	Use
    -0.07
    POSITIVE LOGITS
    /met
    0.07
    ASP
    0.07
    掉了
    0.07
    (pos
    0.07
    召回
    0.07
     mcc
    0.07
    feb
    0.07
     Biggest
    0.07
    BU
    0.07
    国旗
    0.06
    Activations Density 0.007%

    No Known Activations