© 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. 11-RESID-POST-AA
    11. 86873
    Prev
    Next
    INDEX
    Explanations

    sak

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustralian
    -0.08
    歳
    -0.08
     Australian
    -0.08
    夫妇
    -0.07
    뎁
    -0.07
     рамках
    -0.07
     Counts
    -0.07
    auled
    -0.07
    升级改造
    -0.07
    );


↵
    -0.07
    POSITIVE LOGITS
    剂
    0.07
     kita
    0.07
     scient
    0.06
    akit
    0.06
    风筝
    0.06
    有一
    0.06
     kos
    0.06
    uche
    0.06
     capsule
    0.06
     poner
    0.06
    Activations Density 0.008%

    No Known Activations