© 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. 76790
    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_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
    קיימים
    -0.07
    -anchor
    -0.07
     disjoint
    -0.07
    “The
    -0.06
     collaborating
    -0.06
     Travel
    -0.06
    -q
    -0.06
    -reference
    -0.06
    接口
    -0.06
    =msg
    -0.06
    POSITIVE LOGITS
    arcer
    0.08
    BorderStyle
    0.07
     modo
    0.07
    文体
    0.06
     increasingly
    0.06
    perhaps
    0.06
    世家
    0.06
    olan
    0.06
    刳
    0.06
    奓
    0.06
    Activations Density 0.060%

    No Known Activations