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. 35900
    Prev
    Next
    INDEX
    Explanations

    Citations/References

    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
    .person
    -0.08
    متاز
    -0.08
    support
    -0.07
    .alignment
    -0.07
    EATURE
    -0.07
     пациент
    -0.07
     estudiantes
    -0.07
    contributors
    -0.07
    devices
    -0.07
    Offer
    -0.07
    POSITIVE LOGITS
    ê
    0.07
    Clr
    0.07
    宇宙
    0.07
    tr
    0.06
    땸
    0.06
     중심
    0.06
    럴
    0.06
     Chow
    0.06
    �
    0.06
    𝘋
    0.06
    Activations Density 0.194%

    No Known Activations