© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 39957
    Prev
    Next
    INDEX
    Explanations

    Negative tone

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frequently
    -0.07
     Todo
    -0.07
    然
    -0.07
     Tweets
    -0.07
    Wer
    -0.07
    .Signal
    -0.06
    앨
    -0.06
    _defaults
    -0.06
     Fur
    -0.06
    为契机
    -0.06
    POSITIVE LOGITS
    赡
    0.08
     attackers
    0.08
    轿
    0.07
    Descriptors
    0.07
    _workspace
    0.07
    萎缩
    0.07
    溏
    0.07
    ,@
    0.07
    _modify
    0.07
     cooper
    0.07
    Activations Density 0.025%

    No Known Activations