© 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. 19-RESID-POST-AA
    11. 109357
    Prev
    Next
    INDEX
    Explanations

    Negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    确立
    -0.08
    蓄电池
    -0.07
     mainly
    -0.07
     미
    -0.07
     mücade
    -0.07
    とりあえ
    -0.07
    代表大会
    -0.07
    _circle
    -0.07
    步
    -0.07
     honour
    -0.06
    POSITIVE LOGITS
    ssh
    0.07
    一层
    0.07
     Stella
    0.07
    ADD
    0.07
     Jesse
    0.07
     battalion
    0.07
    面料
    0.06
     genres
    0.06
     Hoffman
    0.06
    Behavior
    0.06
    Activations Density 0.012%

    No Known Activations