Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 1998
    Prev
    Next
    INDEX
    Explanations

    antlr lr

    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
     shifts
    -0.08
     HO
    -0.07
    .scrollView
    -0.07
     crib
    -0.07
    SetActive
    -0.07
    。<
    -0.07
    ITT
    -0.07
    Ѽ
    -0.07
    首先是
    -0.07
    为其
    -0.07
    POSITIVE LOGITS
    基金管理
    0.07
     baseman
    0.07
    scenario
    0.07
    に行
    0.06
     pregn
    0.06
    晚饭
    0.06
    tokens
    0.06
     konuş
    0.06
    _SENSOR
    0.06
    achs
    0.06
    Activations Density 0.010%

    No Known Activations