© 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
    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. 110063
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    인지
    -0.08
    ätig
    -0.07
    ausal
    -0.07
    �
    -0.07
    queda
    -0.07
    💼
    -0.07
     marzo
    -0.07
    (grid
    -0.06
    ル
    -0.06
     CSC
    -0.06
    POSITIVE LOGITS
    卖出
    0.07
    c
    0.07
    alias
    0.07
    唐
    0.07
     Frm
    0.07
     Round
    0.07
     donations
    0.06
     algorithm
    0.06
    empl
    0.06
     Compensation
    0.06
    Activations Density 0.014%

    No Known Activations