© 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. 115057
    Prev
    Next
    INDEX
    Explanations

    examples and illustrations

    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
     Nigeria
    -0.07
     Neuroscience
    -0.07
     rescued
    -0.07
    进
    -0.07
     neglect
    -0.07
    宣传片
    -0.07
    -ne
    -0.06
    万达
    -0.06
    _rom
    -0.06
    .UserName
    -0.06
    POSITIVE LOGITS
    מרת
    0.07
    ENSOR
    0.07
    	final
    0.07
    ="/">
    0.07
     ")");↵
    0.07
    ffa
    0.06
    קת
    0.06
     CharSequence
    0.06
    meet
    0.06
     jail
    0.06
    Activations Density 0.021%

    No Known Activations