© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 862
    Prev
    Next
    INDEX
    Explanations

    data processing/communication

    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
    olving
    -0.08
    비스
    -0.07
    indrical
    -0.07
    ovation
    -0.07
    위원장
    -0.07
    /apache
    -0.06
     cylindrical
    -0.06
    _al
    -0.06
    กระบวน
    -0.06
    𠅤
    -0.06
    POSITIVE LOGITS
     Streams
    0.08
    (@"%@",
    0.07
     Starter
    0.07
     runes
    0.07
     Semantic
    0.07
    쿤
    0.07
    yle
    0.07
    都无法
    0.07
     sampled
    0.07
    力争
    0.07
    Activations Density 0.010%

    No Known Activations