© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    Accessor

    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
    钬
    -0.08
    lyphicon
    -0.08
    摩
    -0.07
     respond
    -0.07
    ".$_
    -0.07
    셴
    -0.07
     PROT
    -0.07
     ethnicity
    -0.07
    üstü
    -0.06
    sns
    -0.06
    POSITIVE LOGITS
    🌪
    0.07
     Ли
    0.07
    ái
    0.07
    baum
    0.07
    אור
    0.06
     cached
    0.06
    ashing
    0.06
    )frame
    0.06
    reur
    0.06
     parse
    0.06
    Activations Density 0.000%

    No Known Activations