© 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. 19-RESID-POST-AA
    11. 69302
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dio
    -0.07
     dispon
    -0.07
    Shows
    -0.07
    joy
    -0.07
    평
    -0.07
    提供了
    -0.07
    稿件
    -0.07
    شارك
    -0.07
    edad
    -0.07
     journals
    -0.07
    POSITIVE LOGITS
     Gospel
    0.07
     lemma
    0.06
    _union
    0.06
    瓷
    0.06
     intestinal
    0.06
    (cpu
    0.06
    應用
    0.06
     copied
    0.06
    城市群
    0.06
    𖧷
    0.06
    Activations Density 0.157%

    No Known Activations