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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 60706
    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
     }
↵
↵
↵
    -0.07
    [from
    -0.07
     SEX
    -0.07
    	FROM
    -0.07
    _SEG
    -0.07
    ORMAL
    -0.07
    beh
    -0.07
    -self
    -0.07
     ?></
    -0.07
    	df
    -0.07
    POSITIVE LOGITS
    кладыва
    0.07
     absorbing
    0.07
    пуска
    0.07
     cautiously
    0.07
     russian
    0.07
    ảo
    0.07
    原谅
    0.07
    楽しめる
    0.07
     arty
    0.07
    ij
    0.07
    Activations Density 0.082%

    No Known Activations