© 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. 76162
    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
     banker
    -0.07
    	dest
    -0.07
     undocumented
    -0.07
    暧
    -0.07
     setOpen
    -0.07
    	Vector
    -0.06
     Kabul
    -0.06
    华侨
    -0.06
    米粉
    -0.06
     bet
    -0.06
    POSITIVE LOGITS
    	tr
    0.07
     dataIndex
    0.07
    answered
    0.07
    listening
    0.07
    สว
    0.07
    _routes
    0.06
     число
    0.06
    ӊ
    0.06
    }elseif
    0.06
    잍
    0.06
    Activations Density 0.027%

    No Known Activations