© 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. 15-RESID-POST-AA
    11. 14769
    Prev
    Next
    INDEX
    Explanations

    period

    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_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
    ú
    -0.08
    成立于
    -0.08
     Technician
    -0.07
     technicians
    -0.07
     transplant
    -0.07
     jd
    -0.07
    ße
    -0.07
    稼
    -0.07
     Veteran
    -0.07
     candid
    -0.07
    POSITIVE LOGITS
        ↵
    0.07
    埚
    0.07
    她们
    0.07
    的姿态
    0.06
    ⇇
    0.06
                            ↵
    0.06
    (mut
    0.06
    *p
    0.06
    但
    0.06
    JSGlobal
    0.06
    Activations Density 0.000%

    No Known Activations