© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 77823
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    窸
    -0.09
    ROADCAST
    -0.07
     EXISTS
    -0.07
    ﳎ
    -0.07
    �
    -0.07
     xmlDoc
    -0.07
    莺
    -0.07
    (c
    -0.07
    线上线下
    -0.07
    ᅠ
    -0.07
    POSITIVE LOGITS
     setFrame
    0.07
     isEnabled
    0.07
     premises
    0.07
    Username
    0.07
    已在
    0.07
    "></
    0.07
    'in
    0.07
    	sf
    0.07
     Microsoft
    0.07
    nder
    0.07
    Activations Density 0.001%

    No Known Activations