Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130141
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olle
    -0.07
    tot
    -0.07
    .chain
    -0.07
     Poland
    -0.07
     Tokyo
    -0.07
    register
    -0.07
    isen
    -0.07
     따라
    -0.07
    translation
    -0.07
     Yönet
    -0.06
    POSITIVE LOGITS
    棽
    0.08
    男篮
    0.08
     encryption
    0.07
    ⋼
    0.07
    咺
    0.07
     creepy
    0.07
    でしょうか
    0.06
    -avatar
    0.06
    保護
    0.06
    .iv
    0.06
    Activations Density 0.183%

    No Known Activations