© 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. 15-RESID-POST-AA
    11. 85311
    Prev
    Next
    INDEX
    Explanations

    ($

    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
    转身
    -0.08
    女朋友
    -0.07
    :I
    -0.07
     #
    -0.07
    ardi
    -0.07
    링
    -0.07
    _grupo
    -0.07
     BH
    -0.07
    联手
    -0.07
     SCE
    -0.07
    POSITIVE LOGITS
     secular
    0.07
     los
    0.07
    (poly
    0.07
     the
    0.07
    ꦗ
    0.07
    能够让
    0.07
     propagated
    0.07
     för
    0.06
    体积
    0.06
    iscrimination
    0.06
    Activations Density 0.047%

    No Known Activations